Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 66 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.7995. Min Act: -0.1700
Data Index: 1124984 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.4558. Min Act: -0.1700
Data Index: 4405185 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.3620. Min Act: -0.1700
Data Index: 5179807 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.3620. Min Act: -0.1700
Data Index: 8738291 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.2683. Min Act: -0.1700
Data Index: 4207523 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.0808. Min Act: -0.1700
Data Index: 4139415 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.0808. Min Act: -0.1700
Data Index: 7402046 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7995. Min Range: -7.7995
Max Act: 7.0183. Min Act: -0.1700
Data Index: 2046712 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.9870. Min Act: -0.1700
Data Index: 3723608 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.9558. Min Act: -0.1700
Data Index: 8149841 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.9245. Min Act: -0.1700
Data Index: 2041012 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.9245. Min Act: -0.1700
Data Index: 4862494 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.9245. Min Act: -0.1700
Data Index: 7867863 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.9245. Min Act: -0.1700
Data Index: 3257496 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.8933. Min Act: -0.1700
Data Index: 4455814 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.8933. Min Act: -0.1700
Data Index: 2066222 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.8620. Min Act: -0.1700
Data Index: 3003400 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.8308. Min Act: -0.1700
Data Index: 3644307 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.7995. Min Act: -0.1700
Data Index: 406023 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7995. Min Range: -7.7995
Max Act: 6.8308. Min Act: -0.1700
Data Index: 5885317 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19