Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2275 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.7180. Min Act: -0.1700
Data Index: 7252239 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.6868. Min Act: -0.1700
Data Index: 3242479 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.6868. Min Act: -0.1700
Data Index: 2174191 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.6243. Min Act: -0.1700
Data Index: 504453 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.6243. Min Act: -0.1700
Data Index: 3651125 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.6243. Min Act: -0.1700
Data Index: 1141124 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.6243. Min Act: -0.1700
Data Index: 6041084 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5930. Min Act: -0.1700
Data Index: 4818418 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5305. Min Act: -0.1700
Data Index: 5973220 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5618. Min Act: -0.1700
Data Index: 809029 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5618. Min Act: -0.1700
Data Index: 1011202 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5305. Min Act: -0.1700
Data Index: 256135 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5305. Min Act: -0.1700
Data Index: 4631547 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5305. Min Act: -0.1700
Data Index: 148655 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.5305. Min Act: -0.1700
Data Index: 1970986 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.4993. Min Act: -0.1700
Data Index: 6190816 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.4993. Min Act: -0.1700
Data Index: 8031362 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.4993. Min Act: -0.1700
Data Index: 5715978 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.4993. Min Act: -0.1700
Data Index: 1699638 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7180. Min Range: -4.7180
Max Act: 4.4680. Min Act: -0.1700
Data Index: 2660393 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19