Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.7279. Min Act: -0.1700
Data Index: 7381557 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.6654. Min Act: -0.1700
Data Index: 2777597 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.5717. Min Act: -0.1700
Data Index: 2434381 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.4467. Min Act: -0.1700
Data Index: 5510792 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.4154. Min Act: -0.1700
Data Index: 8813988 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.4467. Min Act: -0.1700
Data Index: 7111798 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.3529. Min Act: -0.1700
Data Index: 344377 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.3842. Min Act: -0.1700
Data Index: 7913088 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.3529. Min Act: -0.1700
Data Index: 3067 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.2904. Min Act: -0.1700
Data Index: 1903765 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.2592. Min Act: -0.1700
Data Index: 2797468 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.1654. Min Act: -0.1700
Data Index: 7002879 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.2279. Min Act: -0.1700
Data Index: 3926403 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.1967. Min Act: -0.1700
Data Index: 7381696 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.1967. Min Act: -0.1700
Data Index: 5537725 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.1342. Min Act: -0.1700
Data Index: 4437322 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.1654. Min Act: -0.1700
Data Index: 8045390 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.1342. Min Act: -0.1700
Data Index: 5749040 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.0717. Min Act: -0.1700
Data Index: 5501725 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7279. Min Range: -7.7279
Max Act: 7.1342. Min Act: -0.1700
Data Index: 8291616 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19