Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4812 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.9338. Min Act: -0.1700
Data Index: 8284918 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.7151. Min Act: -0.1700
Data Index: 5056096 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.6526. Min Act: -0.1700
Data Index: 1398699 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.6526. Min Act: -0.1700
Data Index: 1555252 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.6213. Min Act: -0.1700
Data Index: 8189762 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.6213. Min Act: -0.1700
Data Index: 7445905 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5901. Min Act: -0.1700
Data Index: 823245 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5901. Min Act: -0.1700
Data Index: 8811427 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5901. Min Act: -0.1700
Data Index: 5441 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5588. Min Act: -0.1700
Data Index: 4644767 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5276. Min Act: -0.1700
Data Index: 8382411 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5588. Min Act: -0.1700
Data Index: 2853726 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5588. Min Act: -0.1700
Data Index: 5735990 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5588. Min Act: -0.1700
Data Index: 163054 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5588. Min Act: -0.1700
Data Index: 3183188 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5588. Min Act: -0.1700
Data Index: 3921446 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5588. Min Act: -0.1700
Data Index: 4406171 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5276. Min Act: -0.1700
Data Index: 4180552 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.5276. Min Act: -0.1700
Data Index: 1398700 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9338. Min Range: -5.9338
Max Act: 5.4963. Min Act: -0.1700
Data Index: 8255318 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19