Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 814 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.5779. Min Act: -0.1700
Data Index: 6704395 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.5456. Min Act: -0.1700
Data Index: 6972658 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4646. Min Act: -0.1700
Data Index: 4315515 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4646. Min Act: -0.1700
Data Index: 4261043 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4809. Min Act: -0.1700
Data Index: 3340488 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4484. Min Act: -0.1700
Data Index: 7082627 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4321. Min Act: -0.1700
Data Index: 6594027 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4158. Min Act: -0.1700
Data Index: 2982684 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4158. Min Act: -0.1700
Data Index: 4109511 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4321. Min Act: -0.1700
Data Index: 4535215 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4158. Min Act: -0.1700
Data Index: 6625542 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.3832. Min Act: -0.1700
Data Index: 7529905 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.3995. Min Act: -0.1700
Data Index: 7040129 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.3995. Min Act: -0.1700
Data Index: 2053418 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4158. Min Act: -0.1700
Data Index: 2652585 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.3832. Min Act: -0.1700
Data Index: 5790042 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.3668. Min Act: -0.1700
Data Index: 4454582 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.3832. Min Act: -0.1700
Data Index: 6228291 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.3995. Min Act: -0.1700
Data Index: 7011587 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5779. Min Range: -2.5779
Max Act: 2.4158. Min Act: -0.1700
Data Index: 7836463 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19