Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4681 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.4335. Min Act: -0.1700
Data Index: 4722029 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.3397. Min Act: -0.1700
Data Index: 6970253 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.3397. Min Act: -0.1700
Data Index: 161848 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.0897. Min Act: -0.1700
Data Index: 79339 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.0897. Min Act: -0.1700
Data Index: 971544 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.0897. Min Act: -0.1700
Data Index: 1040664 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.0585. Min Act: -0.1700
Data Index: 5991160 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.0272. Min Act: -0.1700
Data Index: 1582922 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.0272. Min Act: -0.1700
Data Index: 7967721 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4335. Min Range: -4.4335
Max Act: 4.0272. Min Act: -0.1700
Data Index: 1877702 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9647. Min Act: -0.1700
Data Index: 7735191 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9647. Min Act: -0.1700
Data Index: 3118503 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 1623164 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 586027 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 8539327 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 8083129 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 964722 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 7995594 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 2994579 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4335. Min Range: -4.4335
Max Act: 3.9334. Min Act: -0.1700
Data Index: 6317886 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19