Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5054 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.5803. Min Act: -0.1700
Data Index: 7797736 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.4553. Min Act: -0.1700
Data Index: 6494004 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.3303. Min Act: -0.1700
Data Index: 3504964 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.2366. Min Act: -0.1700
Data Index: 3302444 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.2053. Min Act: -0.1700
Data Index: 8311010 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.2053. Min Act: -0.1700
Data Index: 5410765 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.1741. Min Act: -0.1700
Data Index: 8465734 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.1741. Min Act: -0.1700
Data Index: 38932 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.1741. Min Act: -0.1700
Data Index: 5395378 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.1116. Min Act: -0.1700
Data Index: 8546339 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.0803. Min Act: -0.1700
Data Index: 6804337 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.0178. Min Act: -0.1700
Data Index: 7458326 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.0178. Min Act: -0.1700
Data Index: 4577734 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.0178. Min Act: -0.1700
Data Index: 8298469 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.0178. Min Act: -0.1700
Data Index: 5297702 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.0178. Min Act: -0.1700
Data Index: 6826137 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5803. Min Range: -6.5803
Max Act: 6.0178. Min Act: -0.1700
Data Index: 6689497 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5803. Min Range: -6.5803
Max Act: 5.9866. Min Act: -0.1700
Data Index: 1047312 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5803. Min Range: -6.5803
Max Act: 5.9866. Min Act: -0.1700
Data Index: 2421037 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5803. Min Range: -6.5803
Max Act: 5.9866. Min Act: -0.1700
Data Index: 650441 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19