Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5732 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.7068. Min Act: -0.1700
Data Index: 5544198 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.6443. Min Act: -0.1700
Data Index: 5484912 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.6130. Min Act: -0.1700
Data Index: 8168893 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5193. Min Act: -0.1700
Data Index: 577311 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5505. Min Act: -0.1700
Data Index: 7152109 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5505. Min Act: -0.1700
Data Index: 7501601 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5193. Min Act: -0.1700
Data Index: 8436696 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.5505. Min Act: -0.1700
Data Index: 3972443 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4880. Min Act: -0.1700
Data Index: 4338183 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4568. Min Act: -0.1700
Data Index: 2425449 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4568. Min Act: -0.1700
Data Index: 6131718 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.4255. Min Act: -0.1700
Data Index: 3593847 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3943. Min Act: -0.1700
Data Index: 2509490 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3943. Min Act: -0.1700
Data Index: 4364311 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3630. Min Act: -0.1700
Data Index: 4449896 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3630. Min Act: -0.1700
Data Index: 7937492 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3318. Min Act: -0.1700
Data Index: 8712932 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.3005. Min Act: -0.1700
Data Index: 5956257 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.2693. Min Act: -0.1700
Data Index: 2074785 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7068. Min Range: -5.7068
Max Act: 5.2380. Min Act: -0.1700
Data Index: 7115210 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19