Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5965 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3993. Min Range: -7.3993
Max Act: 7.3993. Min Act: -0.1700
Data Index: 3285469 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3993. Min Range: -7.3993
Max Act: 7.3680. Min Act: -0.1700
Data Index: 7036057 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3993. Min Range: -7.3993
Max Act: 7.2430. Min Act: -0.1700
Data Index: 3395326 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3993. Min Range: -7.3993
Max Act: 7.0555. Min Act: -0.1700
Data Index: 1090075 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.9930. Min Act: -0.1700
Data Index: 8443054 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.9305. Min Act: -0.1700
Data Index: 2714225 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8993. Min Act: -0.1700
Data Index: 2958950 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8993. Min Act: -0.1700
Data Index: 4362507 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8368. Min Act: -0.1700
Data Index: 8443053 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8680. Min Act: -0.1700
Data Index: 4082664 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8368. Min Act: -0.1700
Data Index: 5488306 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8993. Min Act: -0.1700
Data Index: 1087476 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8680. Min Act: -0.1700
Data Index: 1882258 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8055. Min Act: -0.1700
Data Index: 8359024 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.7743. Min Act: -0.1700
Data Index: 42812 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.8055. Min Act: -0.1700
Data Index: 5573591 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.7743. Min Act: -0.1700
Data Index: 5964651 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.7430. Min Act: -0.1700
Data Index: 4337382 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.7743. Min Act: -0.1700
Data Index: 2340422 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3993. Min Range: -7.3993
Max Act: 6.7430. Min Act: -0.1700
Data Index: 7309643 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19