Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1382. Min Range: -9.1382
Max Act: 9.1382. Min Act: -0.1700
Data Index: 939254 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1382. Min Range: -9.1382
Max Act: 9.0132. Min Act: -0.1700
Data Index: 4106437 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.8882. Min Act: -0.1700
Data Index: 4231984 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.8257. Min Act: -0.1700
Data Index: 3399262 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7632. Min Act: -0.1700
Data Index: 4476863 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7632. Min Act: -0.1700
Data Index: 777315 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7007. Min Act: -0.1700
Data Index: 247000 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7007. Min Act: -0.1700
Data Index: 3064252 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7007. Min Act: -0.1700
Data Index: 3064251 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7007. Min Act: -0.1700
Data Index: 1223517 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7007. Min Act: -0.1700
Data Index: 459328 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.7007. Min Act: -0.1700
Data Index: 1183396 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.6382. Min Act: -0.1700
Data Index: 4147769 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.6382. Min Act: -0.1700
Data Index: 8811918 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.6382. Min Act: -0.1700
Data Index: 8662579 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.5757. Min Act: -0.1700
Data Index: 834798 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.6382. Min Act: -0.1700
Data Index: 4360931 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.5757. Min Act: -0.1700
Data Index: 1823120 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.5757. Min Act: -0.1700
Data Index: 934962 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1382. Min Range: -9.1382
Max Act: 8.5757. Min Act: -0.1700
Data Index: 2158899 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19