Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.9858. Min Act: -0.1700
Data Index: 3057414 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.8608. Min Act: -0.1700
Data Index: 3185695 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.7358. Min Act: -0.1700
Data Index: 891474 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6733. Min Act: -0.1700
Data Index: 416586 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6733. Min Act: -0.1700
Data Index: 4785350 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6733. Min Act: -0.1700
Data Index: 1719452 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6108. Min Act: -0.1700
Data Index: 1093964 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6108. Min Act: -0.1700
Data Index: 3354809 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6108. Min Act: -0.1700
Data Index: 4674482 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6108. Min Act: -0.1700
Data Index: 5263684 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.6108. Min Act: -0.1700
Data Index: 4119932 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.5483. Min Act: -0.1700
Data Index: 1045405 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.5483. Min Act: -0.1700
Data Index: 5851977 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.5483. Min Act: -0.1700
Data Index: 8814146 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.5483. Min Act: -0.1700
Data Index: 1246823 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.4858. Min Act: -0.1700
Data Index: 3086107 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.4858. Min Act: -0.1700
Data Index: 8506126 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.4858. Min Act: -0.1700
Data Index: 8163167 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.4545. Min Act: -0.1700
Data Index: 6372491 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9858. Min Range: -7.9858
Max Act: 7.4545. Min Act: -0.1700
Data Index: 6967878 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19