Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.7349. Min Act: -0.1700
Data Index: 2362263 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2317339 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.6411. Min Act: -0.1700
Data Index: 4780110 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.5474. Min Act: -0.1700
Data Index: 7336878 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.5474. Min Act: -0.1700
Data Index: 4851326 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.5161. Min Act: -0.1700
Data Index: 3740010 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.4536. Min Act: -0.1700
Data Index: 2640956 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.4536. Min Act: -0.1700
Data Index: 8472719 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.4536. Min Act: -0.1700
Data Index: 803936 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.4224. Min Act: -0.1700
Data Index: 681269 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.4224. Min Act: -0.1700
Data Index: 151686 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.4224. Min Act: -0.1700
Data Index: 926317 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.4224. Min Act: -0.1700
Data Index: 1938728 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.3911. Min Act: -0.1700
Data Index: 4838653 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.3911. Min Act: -0.1700
Data Index: 4244974 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.3911. Min Act: -0.1700
Data Index: 3302967 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.3911. Min Act: -0.1700
Data Index: 238705 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.3286. Min Act: -0.1700
Data Index: 5136304 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.3599. Min Act: -0.1700
Data Index: 183900 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7349. Min Range: -4.7349
Max Act: 4.3286. Min Act: -0.1700
Data Index: 6996831 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19