Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6351 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1369. Min Range: -10.1369
Max Act: 10.1369. Min Act: -0.1700
Data Index: 4795352 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1369. Min Range: -10.1369
Max Act: 10.1369. Min Act: -0.1700
Data Index: 1116506 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1369. Min Range: -10.1369
Max Act: 10.0744. Min Act: -0.1700
Data Index: 6234806 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.8869. Min Act: -0.1700
Data Index: 2089258 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.8869. Min Act: -0.1700
Data Index: 6913491 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6994. Min Act: -0.1700
Data Index: 5872276 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6994. Min Act: -0.1700
Data Index: 8212524 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6994. Min Act: -0.1700
Data Index: 7607135 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.7619. Min Act: -0.1700
Data Index: 6706677 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6994. Min Act: -0.1700
Data Index: 1783739 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6994. Min Act: -0.1700
Data Index: 3377608 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6369. Min Act: -0.1700
Data Index: 2624131 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6369. Min Act: -0.1700
Data Index: 227794 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6369. Min Act: -0.1700
Data Index: 2536994 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6994. Min Act: -0.1700
Data Index: 7622292 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6994. Min Act: -0.1700
Data Index: 8031715 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6369. Min Act: -0.1700
Data Index: 6719361 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6369. Min Act: -0.1700
Data Index: 709478 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.6369. Min Act: -0.1700
Data Index: 5491774 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1369. Min Range: -10.1369
Max Act: 9.5744. Min Act: -0.1700
Data Index: 5763392 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19