Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5009 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.6241. Min Act: -0.1700
Data Index: 7040392 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.4053. Min Act: -0.1700
Data Index: 6043471 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.2491. Min Act: -0.1700
Data Index: 6855693 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.2178. Min Act: -0.1700
Data Index: 1688087 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.1553. Min Act: -0.1700
Data Index: 570571 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.1553. Min Act: -0.1700
Data Index: 2603229 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.1241. Min Act: -0.1700
Data Index: 4959966 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.1241. Min Act: -0.1700
Data Index: 7336003 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.1241. Min Act: -0.1700
Data Index: 3777411 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.0928. Min Act: -0.1700
Data Index: 3200661 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.0616. Min Act: -0.1700
Data Index: 288792 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.0303. Min Act: -0.1700
Data Index: 1114223 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6241. Min Range: -6.6241
Max Act: 5.9991. Min Act: -0.1700
Data Index: 8144523 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6241. Min Range: -6.6241
Max Act: 6.0303. Min Act: -0.1700
Data Index: 4667179 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6241. Min Range: -6.6241
Max Act: 5.9991. Min Act: -0.1700
Data Index: 8022069 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6241. Min Range: -6.6241
Max Act: 5.9991. Min Act: -0.1700
Data Index: 2157388 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6241. Min Range: -6.6241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 3337577 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6241. Min Range: -6.6241
Max Act: 5.9366. Min Act: -0.1700
Data Index: 7738145 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6241. Min Range: -6.6241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 338148 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6241. Min Range: -6.6241
Max Act: 5.9678. Min Act: -0.1700
Data Index: 2273293 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19