Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0389. Min Range: -6.0389
Max Act: 6.0389. Min Act: -0.1700
Data Index: 503518 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.9452. Min Act: -0.1700
Data Index: 3351489 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.8827. Min Act: -0.1700
Data Index: 5886724 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.8514. Min Act: -0.1700
Data Index: 1060620 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.7889. Min Act: -0.1700
Data Index: 442626 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.8202. Min Act: -0.1700
Data Index: 112525 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.7889. Min Act: -0.1700
Data Index: 3156250 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.7577. Min Act: -0.1700
Data Index: 542438 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.7264. Min Act: -0.1700
Data Index: 6406931 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.6952. Min Act: -0.1700
Data Index: 7418419 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.6952. Min Act: -0.1700
Data Index: 2247299 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.6639. Min Act: -0.1700
Data Index: 7833002 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.6639. Min Act: -0.1700
Data Index: 5886447 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.6327. Min Act: -0.1700
Data Index: 1240550 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.6327. Min Act: -0.1700
Data Index: 3276665 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.6014. Min Act: -0.1700
Data Index: 3097266 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.5702. Min Act: -0.1700
Data Index: 5553061 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.5702. Min Act: -0.1700
Data Index: 526075 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.5702. Min Act: -0.1700
Data Index: 5633142 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0389. Min Range: -6.0389
Max Act: 5.5702. Min Act: -0.1700
Data Index: 1641150 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19