Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5851 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.9378. Min Act: -0.1700
Data Index: 1738958 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.8440. Min Act: -0.1700
Data Index: 1409262 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.8440. Min Act: -0.1700
Data Index: 496566 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.7815. Min Act: -0.1700
Data Index: 4313653 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.7503. Min Act: -0.1700
Data Index: 8162538 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.6253. Min Act: -0.1700
Data Index: 5947339 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.5940. Min Act: -0.1700
Data Index: 193313 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.5628. Min Act: -0.1700
Data Index: 2554431 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.5628. Min Act: -0.1700
Data Index: 823523 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.5315. Min Act: -0.1700
Data Index: 1940898 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.5003. Min Act: -0.1700
Data Index: 2650174 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.5315. Min Act: -0.1700
Data Index: 1289016 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.4378. Min Act: -0.1700
Data Index: 4400147 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.4378. Min Act: -0.1700
Data Index: 2464709 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.4065. Min Act: -0.1700
Data Index: 4351640 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.3753. Min Act: -0.1700
Data Index: 1040018 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.3753. Min Act: -0.1700
Data Index: 757356 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.4065. Min Act: -0.1700
Data Index: 6708670 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.3440. Min Act: -0.1700
Data Index: 4233188 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9378. Min Range: -6.9378
Max Act: 6.3440. Min Act: -0.1700
Data Index: 2017328 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19