Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5389. Min Range: -5.5389
Max Act: 5.5389. Min Act: -0.1700
Data Index: 8361381 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5389. Min Range: -5.5389
Max Act: 5.3514. Min Act: -0.1700
Data Index: 2793898 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5389. Min Range: -5.5389
Max Act: 5.1014. Min Act: -0.1700
Data Index: 4836802 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5389. Min Range: -5.5389
Max Act: 5.1014. Min Act: -0.1700
Data Index: 2292821 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5389. Min Range: -5.5389
Max Act: 5.0389. Min Act: -0.1700
Data Index: 7403487 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.9452. Min Act: -0.1700
Data Index: 6637283 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.9139. Min Act: -0.1700
Data Index: 3228062 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.9139. Min Act: -0.1700
Data Index: 5348594 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.9139. Min Act: -0.1700
Data Index: 1951809 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8827. Min Act: -0.1700
Data Index: 4448821 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 477569 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8827. Min Act: -0.1700
Data Index: 2382548 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 2478990 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8202. Min Act: -0.1700
Data Index: 5989816 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8202. Min Act: -0.1700
Data Index: 2480064 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 1499495 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 2380097 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8514. Min Act: -0.1700
Data Index: 3782740 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8202. Min Act: -0.1700
Data Index: 7028270 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5389. Min Range: -5.5389
Max Act: 4.8202. Min Act: -0.1700
Data Index: 6600910 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19