Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 598 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.3394. Min Act: -0.1700
Data Index: 8687534 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.2769. Min Act: -0.1700
Data Index: 5212948 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.2456. Min Act: -0.1700
Data Index: 1518302 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.2144. Min Act: -0.1700
Data Index: 6128851 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.2144. Min Act: -0.1700
Data Index: 6821683 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.1519. Min Act: -0.1700
Data Index: 1919729 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.1206. Min Act: -0.1700
Data Index: 4340789 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.1206. Min Act: -0.1700
Data Index: 7869695 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.0894. Min Act: -0.1700
Data Index: 5636051 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.1206. Min Act: -0.1700
Data Index: 2262048 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.0894. Min Act: -0.1700
Data Index: 163466 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.0894. Min Act: -0.1700
Data Index: 1543242 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.0581. Min Act: -0.1700
Data Index: 6212837 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.0269. Min Act: -0.1700
Data Index: 5527784 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.0269. Min Act: -0.1700
Data Index: 944722 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3394. Min Range: -5.3394
Max Act: 4.9956. Min Act: -0.1700
Data Index: 3644779 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3394. Min Range: -5.3394
Max Act: 4.9956. Min Act: -0.1700
Data Index: 1029653 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3394. Min Range: -5.3394
Max Act: 4.9644. Min Act: -0.1700
Data Index: 1633330 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3394. Min Range: -5.3394
Max Act: 5.0269. Min Act: -0.1700
Data Index: 1029959 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3394. Min Range: -5.3394
Max Act: 4.9956. Min Act: -0.1700
Data Index: 6329284 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19