Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4350 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3166. Min Range: -6.3166
Max Act: 6.3166. Min Act: -0.1700
Data Index: 6586298 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3166. Min Range: -6.3166
Max Act: 6.1291. Min Act: -0.1700
Data Index: 8157299 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3166. Min Range: -6.3166
Max Act: 6.0353. Min Act: -0.1700
Data Index: 1042480 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.9728. Min Act: -0.1700
Data Index: 734241 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.9103. Min Act: -0.1700
Data Index: 7419236 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.8478. Min Act: -0.1700
Data Index: 4617750 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.8166. Min Act: -0.1700
Data Index: 1426185 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.8166. Min Act: -0.1700
Data Index: 5850874 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.8478. Min Act: -0.1700
Data Index: 4351503 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7853. Min Act: -0.1700
Data Index: 691169 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7853. Min Act: -0.1700
Data Index: 60601 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7853. Min Act: -0.1700
Data Index: 367721 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7853. Min Act: -0.1700
Data Index: 34506 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7853. Min Act: -0.1700
Data Index: 5546723 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7541. Min Act: -0.1700
Data Index: 4012852 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7541. Min Act: -0.1700
Data Index: 4565657 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7853. Min Act: -0.1700
Data Index: 5199031 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7228. Min Act: -0.1700
Data Index: 3530270 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.6916. Min Act: -0.1700
Data Index: 696565 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3166. Min Range: -6.3166
Max Act: 5.7228. Min Act: -0.1700
Data Index: 2153691 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19