Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4183 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.5628. Min Act: -0.1700
Data Index: 2109930 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.4690. Min Act: -0.1700
Data Index: 3476542 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.4065. Min Act: -0.1700
Data Index: 205182 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3440. Min Act: -0.1700
Data Index: 2996211 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3128. Min Act: -0.1700
Data Index: 1963107 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.3128. Min Act: -0.1700
Data Index: 6655485 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2815. Min Act: -0.1700
Data Index: 1354289 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2815. Min Act: -0.1700
Data Index: 1999551 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 7602733 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2503. Min Act: -0.1700
Data Index: 909434 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2190. Min Act: -0.1700
Data Index: 1664409 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2190. Min Act: -0.1700
Data Index: 8800250 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.1878. Min Act: -0.1700
Data Index: 2668237 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.2190. Min Act: -0.1700
Data Index: 7059878 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.1878. Min Act: -0.1700
Data Index: 5526394 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4506270 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4623238 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.1565. Min Act: -0.1700
Data Index: 2837032 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.1253. Min Act: -0.1700
Data Index: 6628984 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5628. Min Range: -5.5628
Max Act: 5.1565. Min Act: -0.1700
Data Index: 1727900 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19