Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.4165. Min Act: -0.1700
Data Index: 3078422 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.2915. Min Act: -0.1700
Data Index: 4708970 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.2290. Min Act: -0.1700
Data Index: 4384981 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.1977. Min Act: -0.1700
Data Index: 798893 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.1352. Min Act: -0.1700
Data Index: 4676206 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.1352. Min Act: -0.1700
Data Index: 6824370 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.0727. Min Act: -0.1700
Data Index: 6359797 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.0102. Min Act: -0.1700
Data Index: 4150786 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.0102. Min Act: -0.1700
Data Index: 1360486 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9790. Min Act: -0.1700
Data Index: 6718147 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4165. Min Range: -7.4165
Max Act: 7.0102. Min Act: -0.1700
Data Index: 2412818 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9790. Min Act: -0.1700
Data Index: 3455140 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9790. Min Act: -0.1700
Data Index: 40498 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9477. Min Act: -0.1700
Data Index: 663228 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9165. Min Act: -0.1700
Data Index: 3750852 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9165. Min Act: -0.1700
Data Index: 1412980 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9477. Min Act: -0.1700
Data Index: 2204439 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9165. Min Act: -0.1700
Data Index: 1132999 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.9165. Min Act: -0.1700
Data Index: 6480551 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4165. Min Range: -7.4165
Max Act: 6.8852. Min Act: -0.1700
Data Index: 2082133 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19