Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.9582. Min Act: -0.1700
Data Index: 2220669 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.9269. Min Act: -0.1700
Data Index: 5770387 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.9269. Min Act: -0.1700
Data Index: 1698028 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.9269. Min Act: -0.1700
Data Index: 3583973 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8644. Min Act: -0.1699
Data Index: 3467475 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8332. Min Act: -0.1700
Data Index: 5652870 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8019. Min Act: -0.1700
Data Index: 2011642 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8332. Min Act: -0.1700
Data Index: 4472216 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8019. Min Act: -0.1700
Data Index: 5109480 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8019. Min Act: -0.1700
Data Index: 2087877 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8019. Min Act: -0.1700
Data Index: 206078 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8019. Min Act: -0.1700
Data Index: 355896 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.7707. Min Act: -0.1700
Data Index: 1912619 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8019. Min Act: -0.1700
Data Index: 439033 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.7707. Min Act: -0.1700
Data Index: 8744823 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.8019. Min Act: -0.1700
Data Index: 8015235 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.7707. Min Act: -0.1700
Data Index: 6248388 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.7707. Min Act: -0.1700
Data Index: 7594120 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.7707. Min Act: -0.1700
Data Index: 110855 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9582. Min Range: -5.9582
Max Act: 5.7707. Min Act: -0.1700
Data Index: 2236094 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19