Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2134 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5152. Min Range: -9.5152
Max Act: 9.5152. Min Act: -0.1700
Data Index: 1011315 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5152. Min Range: -9.5152
Max Act: 9.4527. Min Act: -0.1700
Data Index: 8753707 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5152. Min Range: -9.5152
Max Act: 9.0152. Min Act: -0.1700
Data Index: 8293430 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.9527. Min Act: -0.1700
Data Index: 6726013 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.9527. Min Act: -0.1700
Data Index: 7768501 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.9527. Min Act: -0.1700
Data Index: 2524797 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.8902. Min Act: -0.1700
Data Index: 489850 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.8902. Min Act: -0.1700
Data Index: 8594146 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.8902. Min Act: -0.1700
Data Index: 6731023 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7652. Min Act: -0.1700
Data Index: 1733587 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7652. Min Act: -0.1700
Data Index: 5362840 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7652. Min Act: -0.1700
Data Index: 235530 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7652. Min Act: -0.1700
Data Index: 4586675 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7652. Min Act: -0.1700
Data Index: 4587165 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7027. Min Act: -0.1700
Data Index: 3433954 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7027. Min Act: -0.1700
Data Index: 4710141 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7027. Min Act: -0.1700
Data Index: 432389 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7027. Min Act: -0.1700
Data Index: 6125569 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.7027. Min Act: -0.1700
Data Index: 268647 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5152. Min Range: -9.5152
Max Act: 8.5777. Min Act: -0.1700
Data Index: 2447374 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19