Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.5520. Min Act: -0.1700
Data Index: 2631745 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.4895. Min Act: -0.1700
Data Index: 1887492 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.4582. Min Act: -0.1700
Data Index: 3628184 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.3957. Min Act: -0.1700
Data Index: 175938 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.3957. Min Act: -0.1700
Data Index: 2631744 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.3645. Min Act: -0.1700
Data Index: 7065163 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.3645. Min Act: -0.1700
Data Index: 6060671 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.3332. Min Act: -0.1700
Data Index: 4498098 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.3020. Min Act: -0.1700
Data Index: 5993245 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.3020. Min Act: -0.1700
Data Index: 1060801 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2395. Min Act: -0.1700
Data Index: 6579974 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2707. Min Act: -0.1700
Data Index: 6168919 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2707. Min Act: -0.1700
Data Index: 5690823 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2707. Min Act: -0.1700
Data Index: 2348825 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2707. Min Act: -0.1700
Data Index: 8649287 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2395. Min Act: -0.1700
Data Index: 7034066 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2707. Min Act: -0.1700
Data Index: 4726969 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.1770. Min Act: -0.1700
Data Index: 4777299 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2082. Min Act: -0.1700
Data Index: 2017517 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5520. Min Range: -5.5520
Max Act: 5.2082. Min Act: -0.1700
Data Index: 122699 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19