Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.8770. Min Act: -0.1700
Data Index: 936188 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.4708. Min Act: -0.1700
Data Index: 4314437 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.4395. Min Act: -0.1700
Data Index: 6349740 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.3458. Min Act: -0.1700
Data Index: 6966712 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.3770. Min Act: -0.1700
Data Index: 1271112 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.3458. Min Act: -0.1700
Data Index: 76483 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.3145. Min Act: -0.1700
Data Index: 6954977 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.3145. Min Act: -0.1700
Data Index: 8178536 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.2833. Min Act: -0.1700
Data Index: 1887154 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.2833. Min Act: -0.1700
Data Index: 3317287 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.2520. Min Act: -0.1700
Data Index: 7871445 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.2208. Min Act: -0.1700
Data Index: 6010969 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.2208. Min Act: -0.1700
Data Index: 2945345 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.2208. Min Act: -0.1700
Data Index: 4478693 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.1583. Min Act: -0.1700
Data Index: 3404840 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.1583. Min Act: -0.1700
Data Index: 322833 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.1583. Min Act: -0.1700
Data Index: 8657271 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.1583. Min Act: -0.1700
Data Index: 3217229 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.1583. Min Act: -0.1700
Data Index: 4370490 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8770. Min Range: -6.8770
Max Act: 6.1270. Min Act: -0.1700
Data Index: 8059814 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19