Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3444 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.4310. Min Act: -0.1700
Data Index: 5383561 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.3685. Min Act: -0.1700
Data Index: 6295688 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.2748. Min Act: -0.1700
Data Index: 5383562 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.1185. Min Act: -0.1700
Data Index: 6977340 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.1185. Min Act: -0.1700
Data Index: 5383563 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.0560. Min Act: -0.1700
Data Index: 8500899 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.0248. Min Act: -0.1700
Data Index: 423044 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.0248. Min Act: -0.1700
Data Index: 2899417 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.0248. Min Act: -0.1700
Data Index: 6160149 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9935. Min Act: -0.1700
Data Index: 2820663 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9623. Min Act: -0.1700
Data Index: 6729588 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4310. Min Range: -5.4310
Max Act: 5.0248. Min Act: -0.1700
Data Index: 5383565 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9623. Min Act: -0.1700
Data Index: 4457210 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9623. Min Act: -0.1700
Data Index: 4416400 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9935. Min Act: -0.1700
Data Index: 2895217 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9935. Min Act: -0.1700
Data Index: 7781279 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9623. Min Act: -0.1700
Data Index: 75170 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9623. Min Act: -0.1700
Data Index: 4861517 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9623. Min Act: -0.1700
Data Index: 2451506 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4310. Min Range: -5.4310
Max Act: 4.9623. Min Act: -0.1700
Data Index: 185794 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19