Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 861 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.8222. Min Act: -0.1700
Data Index: 925534 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.5722. Min Act: -0.1700
Data Index: 4425999 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.5410. Min Act: -0.1700
Data Index: 1071893 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.5410. Min Act: -0.1700
Data Index: 4351796 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.5097. Min Act: -0.1700
Data Index: 8384843 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.4785. Min Act: -0.1700
Data Index: 7282376 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.4472. Min Act: -0.1700
Data Index: 4647441 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.4472. Min Act: -0.1700
Data Index: 6752455 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.4785. Min Act: -0.1700
Data Index: 265337 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.4472. Min Act: -0.1700
Data Index: 8542133 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.4160. Min Act: -0.1700
Data Index: 7713033 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.4160. Min Act: -0.1700
Data Index: 5016274 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3847. Min Act: -0.1700
Data Index: 3952391 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3847. Min Act: -0.1700
Data Index: 5220991 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3847. Min Act: -0.1700
Data Index: 4569580 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3535. Min Act: -0.1700
Data Index: 8602753 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3535. Min Act: -0.1700
Data Index: 1335013 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3222. Min Act: -0.1700
Data Index: 4036607 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3222. Min Act: -0.1700
Data Index: 3298081 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8222. Min Range: -4.8222
Max Act: 4.3222. Min Act: -0.1700
Data Index: 2166684 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19