Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3626. Min Range: -6.3626
Max Act: 6.3626. Min Act: -0.1700
Data Index: 29735 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3626. Min Range: -6.3626
Max Act: 6.2376. Min Act: -0.1700
Data Index: 7874557 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.9876. Min Act: -0.1700
Data Index: 7371076 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.9876. Min Act: -0.1700
Data Index: 704512 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.9251. Min Act: -0.1700
Data Index: 4446393 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8626. Min Act: -0.1700
Data Index: 5699689 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8626. Min Act: -0.1700
Data Index: 8426025 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8313. Min Act: -0.1700
Data Index: 555486 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8626. Min Act: -0.1700
Data Index: 8072805 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8001. Min Act: -0.1700
Data Index: 8297286 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7246550 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8313. Min Act: -0.1700
Data Index: 5707249 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8313. Min Act: -0.1700
Data Index: 6342582 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8001. Min Act: -0.1700
Data Index: 4746192 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.7688. Min Act: -0.1700
Data Index: 4173443 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.7688. Min Act: -0.1700
Data Index: 6052405 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.7688. Min Act: -0.1700
Data Index: 5884178 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.7688. Min Act: -0.1700
Data Index: 1512781 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.8001. Min Act: -0.1700
Data Index: 6434647 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3626. Min Range: -6.3626
Max Act: 5.7688. Min Act: -0.1700
Data Index: 8388518 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19