Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 368 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3843. Min Range: -3.3843
Max Act: 3.3843. Min Act: -0.1700
Data Index: 7546887 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3843. Min Range: -3.3843
Max Act: 3.0857. Min Act: -0.1700
Data Index: 3926678 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3843. Min Range: -3.3843
Max Act: 3.0383. Min Act: -0.1700
Data Index: 6542803 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3843. Min Range: -3.3843
Max Act: 3.0383. Min Act: -0.1700
Data Index: 5590496 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3843. Min Range: -3.3843
Max Act: 3.0226. Min Act: -0.1700
Data Index: 1034129 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3843. Min Range: -3.3843
Max Act: 3.0068. Min Act: -0.1700
Data Index: 7959273 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.9751. Min Act: -0.1700
Data Index: 2886720 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.9751. Min Act: -0.1689
Data Index: 8340554 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8642. Min Act: -0.1700
Data Index: 1562772 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8483. Min Act: -0.1700
Data Index: 2606615 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8483. Min Act: -0.1700
Data Index: 8758243 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8483. Min Act: -0.1697
Data Index: 4265326 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8165. Min Act: -0.1700
Data Index: 2936032 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8006. Min Act: -0.1700
Data Index: 1180117 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8324. Min Act: -0.1700
Data Index: 6763290 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8006. Min Act: -0.1700
Data Index: 528243 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8165. Min Act: -0.1700
Data Index: 1359573 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8483. Min Act: -0.1700
Data Index: 3994564 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8165. Min Act: -0.1700
Data Index: 3310997 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3843. Min Range: -3.3843
Max Act: 2.8324. Min Act: -0.1700
Data Index: 4663187 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19