Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.6117. Min Act: -0.1700
Data Index: 3925084 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.2992. Min Act: -0.1700
Data Index: 6396840 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.1742. Min Act: -0.1700
Data Index: 2264010 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.1429. Min Act: -0.1700
Data Index: 8660977 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.1742. Min Act: -0.1700
Data Index: 7532653 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.0492. Min Act: -0.1700
Data Index: 8525815 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.0179. Min Act: -0.1700
Data Index: 8167798 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.0179. Min Act: -0.1700
Data Index: 894384 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.0179. Min Act: -0.1700
Data Index: 1637691 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6117. Min Range: -7.6117
Max Act: 7.0179. Min Act: -0.1700
Data Index: 4047732 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.9867. Min Act: -0.1700
Data Index: 430110 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.9554. Min Act: -0.1700
Data Index: 2683175 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.8929. Min Act: -0.1700
Data Index: 2846949 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.9242. Min Act: -0.1700
Data Index: 7277136 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.9242. Min Act: -0.1700
Data Index: 4562184 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.8929. Min Act: -0.1700
Data Index: 3898743 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.8929. Min Act: -0.1700
Data Index: 1930583 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.8304. Min Act: -0.1700
Data Index: 4883923 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.8617. Min Act: -0.1700
Data Index: 8027017 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6117. Min Range: -7.6117
Max Act: 6.8304. Min Act: -0.1700
Data Index: 1335305 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19