Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5545 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.9207. Min Act: -0.1700
Data Index: 3417760 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7957. Min Act: -0.1700
Data Index: 226267 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7645. Min Act: -0.1700
Data Index: 7549561 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7332. Min Act: -0.1700
Data Index: 1552831 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7332. Min Act: -0.1700
Data Index: 5931718 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7020. Min Act: -0.1698
Data Index: 5435067 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7020. Min Act: -0.1700
Data Index: 8728863 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7020. Min Act: -0.1700
Data Index: 6258231 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7020. Min Act: -0.1700
Data Index: 965512 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.7020. Min Act: -0.1700
Data Index: 2929345 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6707. Min Act: -0.1700
Data Index: 2813597 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6707. Min Act: -0.1700
Data Index: 377768 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7664548 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6082. Min Act: -0.1700
Data Index: 4754047 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6395. Min Act: -0.1700
Data Index: 3738941 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6395. Min Act: -0.1700
Data Index: 2829552 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6082. Min Act: -0.1700
Data Index: 8454389 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6082. Min Act: -0.1700
Data Index: 6422625 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6082. Min Act: -0.1700
Data Index: 7087013 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9207. Min Range: -5.9207
Max Act: 5.6082. Min Act: -0.1700
Data Index: 1238877 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19