Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2838 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5159. Min Range: -8.5159
Max Act: 8.5159. Min Act: -0.1700
Data Index: 7557094 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.4222. Min Act: -0.1700
Data Index: 2846387 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.3284. Min Act: -0.1700
Data Index: 4133907 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.2034. Min Act: -0.1700
Data Index: 1443938 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.2034. Min Act: -0.1700
Data Index: 7267650 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.2034. Min Act: -0.1700
Data Index: 8745926 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.1722. Min Act: -0.1700
Data Index: 2308620 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.1722. Min Act: -0.1700
Data Index: 7686806 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.1097. Min Act: -0.1700
Data Index: 6973396 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.1409. Min Act: -0.1700
Data Index: 1110644 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.1097. Min Act: -0.1700
Data Index: 48140 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.1097. Min Act: -0.1700
Data Index: 6699014 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.1097. Min Act: -0.1700
Data Index: 6426731 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.0784. Min Act: -0.1700
Data Index: 1487337 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.0472. Min Act: -0.1700
Data Index: 6616716 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.0784. Min Act: -0.1700
Data Index: 6956218 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.0472. Min Act: -0.1700
Data Index: 5172026 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5159. Min Range: -8.5159
Max Act: 7.0784. Min Act: -0.1700
Data Index: 7639510 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5159. Min Range: -8.5159
Max Act: 6.9847. Min Act: -0.1700
Data Index: 6499006 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5159. Min Range: -8.5159
Max Act: 6.9847. Min Act: -0.1700
Data Index: 6631453 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #19