Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.5202. Min Act: -0.1700
Data Index: 1587825 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.4264. Min Act: -0.1700
Data Index: 6451278 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.4577. Min Act: -0.1700
Data Index: 8049297 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.4264. Min Act: -0.1700
Data Index: 6001618 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.3327. Min Act: -0.1700
Data Index: 6071016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.3014. Min Act: -0.1697
Data Index: 3185548 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 4036450 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.3014. Min Act: -0.1700
Data Index: 2645718 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.3014. Min Act: -0.1700
Data Index: 930936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 7823270 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 2032406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 8386310 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 7048953 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 884476 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 6150699 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 4626352 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2702. Min Act: -0.1700
Data Index: 4490828 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2389. Min Act: -0.1700
Data Index: 2008930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2077. Min Act: -0.1700
Data Index: 521033 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5202. Min Range: -5.5202
Max Act: 5.2077. Min Act: -0.1700
Data Index: 2012106 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19