Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1840 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.2186. Min Act: -0.1696
Data Index: 6615726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0769. Min Act: -0.1699
Data Index: 2465577 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0612. Min Act: -0.1693
Data Index: 2362165 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0612. Min Act: -0.1699
Data Index: 3952079 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0454. Min Act: -0.1700
Data Index: 4592065 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0296. Min Act: -0.1700
Data Index: 5893753 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0454. Min Act: -0.1700
Data Index: 4660257 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0138. Min Act: -0.1700
Data Index: 5960225 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0138. Min Act: -0.1700
Data Index: 8301529 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0138. Min Act: -0.1698
Data Index: 5852490 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2186. Min Range: -3.2186
Max Act: 3.0138. Min Act: -0.1700
Data Index: 6998137 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9980. Min Act: -0.1700
Data Index: 5036465 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9980. Min Act: -0.1700
Data Index: 3196481 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9822. Min Act: -0.1700
Data Index: 2078230 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9664. Min Act: -0.1700
Data Index: 2914920 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9664. Min Act: -0.1700
Data Index: 7215928 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9664. Min Act: -0.1700
Data Index: 5022456 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9664. Min Act: -0.1696
Data Index: 6456211 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9664. Min Act: -0.1700
Data Index: 332747 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2186. Min Range: -3.2186
Max Act: 2.9505. Min Act: -0.1699
Data Index: 2602701 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19