Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5181 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.6770. Min Act: -0.1700
Data Index: 2856952 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.5520. Min Act: -0.1700
Data Index: 5040284 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.5520. Min Act: -0.1700
Data Index: 6568877 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.5520. Min Act: -0.1700
Data Index: 5311454 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.4895. Min Act: -0.1700
Data Index: 6432613 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.3957. Min Act: -0.1700
Data Index: 2801374 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.3957. Min Act: -0.1700
Data Index: 4575537 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.4270. Min Act: -0.1700
Data Index: 2678872 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.3645. Min Act: -0.1700
Data Index: 4575538 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.3645. Min Act: -0.1700
Data Index: 8690169 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.3332. Min Act: -0.1700
Data Index: 6112847 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.3332. Min Act: -0.1700
Data Index: 4836528 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.3020. Min Act: -0.1700
Data Index: 2182349 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.2707. Min Act: -0.1700
Data Index: 6291102 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.2707. Min Act: -0.1700
Data Index: 5213934 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.2707. Min Act: -0.1700
Data Index: 4456704 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.2707. Min Act: -0.1700
Data Index: 2714525 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.2395. Min Act: -0.1700
Data Index: 4901058 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.2082. Min Act: -0.1700
Data Index: 792048 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6770. Min Range: -4.6770
Max Act: 4.2082. Min Act: -0.1700
Data Index: 6591473 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19