Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.7125. Min Act: -0.1700
Data Index: 8305816 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.5250. Min Act: -0.1700
Data Index: 1047480 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.4625. Min Act: -0.1700
Data Index: 4164818 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.4000. Min Act: -0.1700
Data Index: 8040701 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.4000. Min Act: -0.1700
Data Index: 1522154 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.2750. Min Act: -0.1700
Data Index: 937906 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.1500. Min Act: -0.1700
Data Index: 5821031 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.0250. Min Act: -0.1700
Data Index: 6445186 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7125. Min Range: -8.7125
Max Act: 8.0250. Min Act: -0.1700
Data Index: 7492163 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.9625. Min Act: -0.1700
Data Index: 2235564 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.8375. Min Act: -0.1700
Data Index: 5739323 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.9000. Min Act: -0.1700
Data Index: 7409907 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.9000. Min Act: -0.1700
Data Index: 6358930 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.9000. Min Act: -0.1700
Data Index: 6788717 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.8375. Min Act: -0.1700
Data Index: 2579557 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.8375. Min Act: -0.1700
Data Index: 8718536 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.7750. Min Act: -0.1700
Data Index: 2252833 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.7750. Min Act: -0.1700
Data Index: 8057475 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.7750. Min Act: -0.1700
Data Index: 5966961 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7125. Min Range: -8.7125
Max Act: 7.7750. Min Act: -0.1700
Data Index: 5194579 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19