Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 202 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2123. Min Range: -1.2123
Max Act: 1.2123. Min Act: -0.1700
Data Index: 4437721 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2123. Min Range: -1.2123
Max Act: 1.2123. Min Act: -0.1700
Data Index: 7720946 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2123. Min Range: -1.2123
Max Act: 1.0369. Min Act: -0.1700
Data Index: 1625450 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9935. Min Act: -0.1700
Data Index: 561303 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9848. Min Act: -0.1700
Data Index: 7596253 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9502. Min Act: -0.1700
Data Index: 4439686 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9416. Min Act: -0.1700
Data Index: 6319336 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9416. Min Act: -0.1700
Data Index: 4402888 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9244. Min Act: -0.1700
Data Index: 4724117 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9244. Min Act: -0.1700
Data Index: 3734398 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.9244. Min Act: -0.1700
Data Index: 4277076 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8987. Min Act: -0.1700
Data Index: 2149172 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8987. Min Act: -0.1700
Data Index: 5963032 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8731. Min Act: -0.1700
Data Index: 8689420 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8476. Min Act: -0.1700
Data Index: 4595275 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8476. Min Act: -0.1700
Data Index: 1654158 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8476. Min Act: -0.1700
Data Index: 3414309 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8476. Min Act: -0.1700
Data Index: 1537351 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8392. Min Act: -0.1700
Data Index: 5442377 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2123. Min Range: -1.2123
Max Act: 0.8392. Min Act: -0.1700
Data Index: 3083468 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19