Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.6070. Min Act: -0.1700
Data Index: 7376093 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.4195. Min Act: -0.1700
Data Index: 1132652 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.4195. Min Act: -0.1700
Data Index: 8669431 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.4195. Min Act: -0.1700
Data Index: 5607501 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.3570. Min Act: -0.1700
Data Index: 2766881 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.3570. Min Act: -0.1700
Data Index: 1080982 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.2945. Min Act: -0.1700
Data Index: 4972502 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.2320. Min Act: -0.1700
Data Index: 6313230 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.1695. Min Act: -0.1700
Data Index: 3343750 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.1695. Min Act: -0.1700
Data Index: 3113621 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.1695. Min Act: -0.1700
Data Index: 2220542 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.1695. Min Act: -0.1700
Data Index: 993866 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.1070. Min Act: -0.1700
Data Index: 8512572 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.1070. Min Act: -0.1700
Data Index: 4353479 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.6070. Min Range: -14.6070
Max Act: 13.9820. Min Act: -0.1700
Data Index: 1257409 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.0445. Min Act: -0.1700
Data Index: 5155798 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.0445. Min Act: -0.1699
Data Index: 999348 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.0445. Min Act: -0.1700
Data Index: 2499143 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.0445. Min Act: -0.1700
Data Index: 1186537 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.6070. Min Range: -14.6070
Max Act: 14.0445. Min Act: -0.1700
Data Index: 3319776 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19