Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1082. Min Range: -6.1082
Max Act: 6.1082. Min Act: -0.1700
Data Index: 3219950 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7019. Min Act: -0.1700
Data Index: 8667549 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.7019. Min Act: -0.1700
Data Index: 4445776 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.6394. Min Act: -0.1700
Data Index: 5198230 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5769. Min Act: -0.1700
Data Index: 8490140 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5457. Min Act: -0.1700
Data Index: 1606975 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5457. Min Act: -0.1700
Data Index: 830040 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5144. Min Act: -0.1700
Data Index: 8738597 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.5144. Min Act: -0.1700
Data Index: 2121979 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4832. Min Act: -0.1700
Data Index: 4389029 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4832. Min Act: -0.1700
Data Index: 8250178 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4519. Min Act: -0.1700
Data Index: 2122488 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4519. Min Act: -0.1700
Data Index: 855302 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4207. Min Act: -0.1700
Data Index: 5711139 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4519. Min Act: -0.1700
Data Index: 1546279 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4207. Min Act: -0.1700
Data Index: 2770920 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4207. Min Act: -0.1700
Data Index: 3788621 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4207. Min Act: -0.1700
Data Index: 8724319 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4207. Min Act: -0.1700
Data Index: 4724469 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1082. Min Range: -6.1082
Max Act: 5.4207. Min Act: -0.1700
Data Index: 7481064 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19