Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3085 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.5628. Min Act: -0.1700
Data Index: 4563366 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.5315. Min Act: -0.1700
Data Index: 365371 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.2190. Min Act: -0.1700
Data Index: 4102038 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.0315. Min Act: -0.1700
Data Index: 5466233 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.0628. Min Act: -0.1700
Data Index: 772364 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.0315. Min Act: -0.1700
Data Index: 684769 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.0003. Min Act: -0.1700
Data Index: 8728564 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5628. Min Range: -6.5628
Max Act: 6.0003. Min Act: -0.1700
Data Index: 2251228 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9690. Min Act: -0.1700
Data Index: 3007570 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9690. Min Act: -0.1700
Data Index: 6201311 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9065. Min Act: -0.1700
Data Index: 715989 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9378. Min Act: -0.1700
Data Index: 8818258 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9065. Min Act: -0.1700
Data Index: 1783269 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9065. Min Act: -0.1700
Data Index: 6105442 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.8753. Min Act: -0.1700
Data Index: 133375 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9065. Min Act: -0.1700
Data Index: 5804750 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9065. Min Act: -0.1700
Data Index: 113273 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.8753. Min Act: -0.1700
Data Index: 4162482 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.9065. Min Act: -0.1700
Data Index: 4327294 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5628. Min Range: -6.5628
Max Act: 5.8440. Min Act: -0.1700
Data Index: 7038901 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19