Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1529 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1802. Min Range: -12.1802
Max Act: 12.1802. Min Act: -0.1700
Data Index: 3182907 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.9927. Min Act: -0.1700
Data Index: 6363239 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.9302. Min Act: -0.1700
Data Index: 7462791 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.8677. Min Act: -0.1700
Data Index: 422984 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.8052. Min Act: -0.1700
Data Index: 2100163 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.7427. Min Act: -0.1700
Data Index: 333665 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.6802. Min Act: -0.1700
Data Index: 5870021 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.7427. Min Act: -0.1700
Data Index: 262342 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.7427. Min Act: -0.1700
Data Index: 7538735 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.6802. Min Act: -0.1700
Data Index: 262344 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.6177. Min Act: -0.1700
Data Index: 2308260 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.6177. Min Act: -0.1700
Data Index: 6615980 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.5552. Min Act: -0.1700
Data Index: 6750308 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.5552. Min Act: -0.1700
Data Index: 1184625 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.5552. Min Act: -0.1700
Data Index: 2234893 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.5552. Min Act: -0.1700
Data Index: 3793023 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.5552. Min Act: -0.1700
Data Index: 1751754 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.5552. Min Act: -0.1700
Data Index: 5949113 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.4927. Min Act: -0.1700
Data Index: 1960088 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1802. Min Range: -12.1802
Max Act: 11.4927. Min Act: -0.1700
Data Index: 2557154 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19