Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1070. Min Range: -10.1070
Max Act: 10.1070. Min Act: -0.1700
Data Index: 1181084 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.7945. Min Act: -0.1700
Data Index: 2972602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.7945. Min Act: -0.1700
Data Index: 4516327 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.7320. Min Act: -0.1700
Data Index: 2782736 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.6695. Min Act: -0.1700
Data Index: 4173588 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.5445. Min Act: -0.1700
Data Index: 1271027 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.5445. Min Act: -0.1700
Data Index: 3747789 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.4820. Min Act: -0.1700
Data Index: 5577311 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.4820. Min Act: -0.1700
Data Index: 7775275 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.4195. Min Act: -0.1700
Data Index: 1644782 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.4820. Min Act: -0.1700
Data Index: 3722166 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.3570. Min Act: -0.1700
Data Index: 8624795 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.3570. Min Act: -0.1700
Data Index: 5710643 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.2945. Min Act: -0.1700
Data Index: 6824121 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.2320. Min Act: -0.1700
Data Index: 5930728 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.2945. Min Act: -0.1700
Data Index: 1388682 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.1695. Min Act: -0.1700
Data Index: 6595151 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.2320. Min Act: -0.1700
Data Index: 1378111 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.2320. Min Act: -0.1700
Data Index: 3187086 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1070. Min Range: -10.1070
Max Act: 9.2320. Min Act: -0.1700
Data Index: 7593394 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19