Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3195 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1169. Min Range: -7.1169
Max Act: 7.1169. Min Act: -0.1700
Data Index: 1723779 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1169. Min Range: -7.1169
Max Act: 7.1169. Min Act: -0.1700
Data Index: 2372197 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1169. Min Range: -7.1169
Max Act: 7.0857. Min Act: -0.1700
Data Index: 3631882 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1169. Min Range: -7.1169
Max Act: 7.0544. Min Act: -0.1700
Data Index: 5442990 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8982. Min Act: -0.1700
Data Index: 575690 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8669. Min Act: -0.1700
Data Index: 179844 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8982. Min Act: -0.1700
Data Index: 5279015 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.9294. Min Act: -0.1700
Data Index: 6176341 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8669. Min Act: -0.1700
Data Index: 374312 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8669. Min Act: -0.1700
Data Index: 8335467 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8669. Min Act: -0.1700
Data Index: 5064559 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8357. Min Act: -0.1700
Data Index: 4622847 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8357. Min Act: -0.1700
Data Index: 7538195 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8357. Min Act: -0.1700
Data Index: 975867 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8357. Min Act: -0.1700
Data Index: 2288247 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8357. Min Act: -0.1700
Data Index: 175654 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8357. Min Act: -0.1700
Data Index: 7109923 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8044. Min Act: -0.1700
Data Index: 154290 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8044. Min Act: -0.1700
Data Index: 2276811 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1169. Min Range: -7.1169
Max Act: 6.8044. Min Act: -0.1700
Data Index: 7148224 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19