Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2077 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0418. Min Range: -3.0418
Max Act: 3.0418. Min Act: -0.1700
Data Index: 7063982 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9628. Min Act: -0.1700
Data Index: 3506318 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9469. Min Act: -0.1700
Data Index: 7447738 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 2465728 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 8818725 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8994. Min Act: -0.1700
Data Index: 3017418 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8677. Min Act: -0.1700
Data Index: 5386864 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8677. Min Act: -0.1700
Data Index: 6921994 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8518. Min Act: -0.1700
Data Index: 3418319 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8518. Min Act: -0.1700
Data Index: 7723316 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8518. Min Act: -0.1700
Data Index: 1490717 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8200. Min Act: -0.1700
Data Index: 1686317 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8041. Min Act: -0.1700
Data Index: 4961681 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8200. Min Act: -0.1700
Data Index: 1759882 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8359. Min Act: -0.1700
Data Index: 1170857 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8200. Min Act: -0.1700
Data Index: 3493694 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8200. Min Act: -0.1700
Data Index: 5070552 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8041. Min Act: -0.1700
Data Index: 945219 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8041. Min Act: -0.1700
Data Index: 4722971 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.7881. Min Act: -0.1700
Data Index: 2151390 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19