Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5130 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.3422. Min Act: -0.1700
Data Index: 8192429 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.3422. Min Act: -0.1700
Data Index: 4051459 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.3110. Min Act: -0.1700
Data Index: 2257057 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.3110. Min Act: -0.1700
Data Index: 389726 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2797. Min Act: -0.1699
Data Index: 3098543 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2485. Min Act: -0.1700
Data Index: 8650847 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2485. Min Act: -0.1700
Data Index: 3052017 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2485. Min Act: -0.1700
Data Index: 7673038 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2485. Min Act: -0.1700
Data Index: 4032107 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2485. Min Act: -0.1700
Data Index: 2075246 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2485. Min Act: -0.1700
Data Index: 8380750 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2485. Min Act: -0.1700
Data Index: 3939926 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 2571746 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 5207439 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 5206824 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 5986103 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 4555987 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 1602730 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 1618519 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3422. Min Range: -6.3422
Max Act: 6.2172. Min Act: -0.1700
Data Index: 2975322 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19