Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3720 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.6393. Min Act: -0.1700
Data Index: 4577978 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.6044. Min Act: -0.1700
Data Index: 7801612 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5695. Min Act: -0.1700
Data Index: 464319 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5344. Min Act: -0.1685
Data Index: 5030011 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5257. Min Act: -0.1700
Data Index: 4577981 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5257. Min Act: -0.1700
Data Index: 4577979 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5257. Min Act: -0.1700
Data Index: 5618383 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5081. Min Act: -0.1700
Data Index: 4029678 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4993. Min Act: -0.1700
Data Index: 4029671 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5081. Min Act: -0.1700
Data Index: 4029659 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5081. Min Act: -0.1700
Data Index: 4577980 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4906. Min Act: -0.1700
Data Index: 7354518 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.5081. Min Act: -0.1700
Data Index: 464315 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4906. Min Act: -0.1700
Data Index: 464312 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4818. Min Act: -0.1700
Data Index: 6076713 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4818. Min Act: -0.1700
Data Index: 4595958 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4993. Min Act: -0.1699
Data Index: 402622 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4818. Min Act: -0.1700
Data Index: 2516613 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4730. Min Act: -0.1700
Data Index: 4029677 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6393. Min Range: -1.6393
Max Act: 1.4730. Min Act: -0.1700
Data Index: 4577989 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19