Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 334 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.7404. Min Act: -0.1700
Data Index: 7381612 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.6779. Min Act: -0.1700
Data Index: 4923176 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.6467. Min Act: -0.1700
Data Index: 230259 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.5217. Min Act: -0.1700
Data Index: 8795112 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.5217. Min Act: -0.1700
Data Index: 310100 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.4592. Min Act: -0.1700
Data Index: 6897524 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.4592. Min Act: -0.1700
Data Index: 3479491 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.4279. Min Act: -0.1700
Data Index: 2068226 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3654. Min Act: -0.1700
Data Index: 3980932 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.4279. Min Act: -0.1700
Data Index: 3551404 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3654. Min Act: -0.1700
Data Index: 3479472 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3967. Min Act: -0.1700
Data Index: 78667 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3654. Min Act: -0.1700
Data Index: 1562151 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3654. Min Act: -0.1700
Data Index: 4923189 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3654. Min Act: -0.1700
Data Index: 1685244 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3654. Min Act: -0.1700
Data Index: 3409340 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3967. Min Act: -0.1700
Data Index: 8114490 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3342. Min Act: -0.1700
Data Index: 8559649 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3342. Min Act: -0.1700
Data Index: 7446550 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7404. Min Range: -5.7404
Max Act: 5.3342. Min Act: -0.1700
Data Index: 6753355 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19