Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.3166. Min Act: -0.1700
Data Index: 6524158 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.2228. Min Act: -0.1700
Data Index: 1385945 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.2228. Min Act: -0.1700
Data Index: 32964 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 6432876 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 2341118 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 2594292 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.1291. Min Act: -0.1700
Data Index: 6448004 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.0666. Min Act: -0.1700
Data Index: 2295747 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.0666. Min Act: -0.1700
Data Index: 4498301 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.0666. Min Act: -0.1700
Data Index: 7037853 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.0666. Min Act: -0.1700
Data Index: 1832769 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.0041. Min Act: -0.1700
Data Index: 8156852 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.0041. Min Act: -0.1700
Data Index: 5158876 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3166. Min Range: -7.3166
Max Act: 6.9728. Min Act: -0.1700
Data Index: 7306884 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3166. Min Range: -7.3166
Max Act: 7.0041. Min Act: -0.1700
Data Index: 6583865 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3166. Min Range: -7.3166
Max Act: 6.9416. Min Act: -0.1700
Data Index: 683631 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3166. Min Range: -7.3166
Max Act: 6.9103. Min Act: -0.1700
Data Index: 7759936 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3166. Min Range: -7.3166
Max Act: 6.9103. Min Act: -0.1700
Data Index: 3952814 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3166. Min Range: -7.3166
Max Act: 6.9103. Min Act: -0.1700
Data Index: 1031316 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3166. Min Range: -7.3166
Max Act: 6.8791. Min Act: -0.1700
Data Index: 5537456 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19