Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1652 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.7365. Min Act: -0.1700
Data Index: 4322305 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.7677. Min Act: -0.1700
Data Index: 2668309 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.6740. Min Act: -0.1700
Data Index: 7307990 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.7052. Min Act: -0.1700
Data Index: 1567827 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.6427. Min Act: -0.1700
Data Index: 8102064 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.6427. Min Act: -0.1700
Data Index: 1807087 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.6115. Min Act: -0.1700
Data Index: 8245105 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.5802. Min Act: -0.1700
Data Index: 6090802 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.5490. Min Act: -0.1700
Data Index: 5957478 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.5490. Min Act: -0.1700
Data Index: 8021973 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.4865. Min Act: -0.1700
Data Index: 1930519 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.5177. Min Act: -0.1700
Data Index: 1647032 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.4552. Min Act: -0.1700
Data Index: 7785081 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.4552. Min Act: -0.1700
Data Index: 6987392 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.4552. Min Act: -0.1700
Data Index: 1608315 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.3615. Min Act: -0.1700
Data Index: 2935197 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.3927. Min Act: -0.1700
Data Index: 882727 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.3927. Min Act: -0.1700
Data Index: 8448994 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.3615. Min Act: -0.1700
Data Index: 7410168 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7677. Min Range: -6.7677
Max Act: 6.3927. Min Act: -0.1700
Data Index: 3862486 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19