Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0366. Min Range: -7.0366
Max Act: 7.0366. Min Act: -0.1700
Data Index: 8445547 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.9428. Min Act: -0.1700
Data Index: 3631407 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.8803. Min Act: -0.1700
Data Index: 2685548 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.8803. Min Act: -0.1700
Data Index: 6451160 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.6616. Min Act: -0.1700
Data Index: 6451159 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.5991. Min Act: -0.1700
Data Index: 3556000 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.5678. Min Act: -0.1700
Data Index: 5515871 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.5678. Min Act: -0.1700
Data Index: 6397606 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.6303. Min Act: -0.1700
Data Index: 7870817 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.5366. Min Act: -0.1700
Data Index: 1493688 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.5366. Min Act: -0.1700
Data Index: 3417446 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.5053. Min Act: -0.1700
Data Index: 4831367 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.4741. Min Act: -0.1700
Data Index: 5528970 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.4741. Min Act: -0.1700
Data Index: 192908 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.4741. Min Act: -0.1700
Data Index: 2871674 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.4428. Min Act: -0.1700
Data Index: 7739204 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.4428. Min Act: -0.1700
Data Index: 1808773 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.4116. Min Act: -0.1700
Data Index: 2807428 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.4428. Min Act: -0.1700
Data Index: 4000112 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0366. Min Range: -7.0366
Max Act: 6.3803. Min Act: -0.1700
Data Index: 5434768 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19