Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5522 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.9313. Min Act: -0.1700
Data Index: 6684109 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 6657056 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.5563. Min Act: -0.1700
Data Index: 3614209 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.4938. Min Act: -0.1700
Data Index: 3059041 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.4000. Min Act: -0.1700
Data Index: 1527450 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.3688. Min Act: -0.1700
Data Index: 2848518 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.3375. Min Act: -0.1700
Data Index: 7045288 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.3375. Min Act: -0.1700
Data Index: 1758261 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.2750. Min Act: -0.1700
Data Index: 3405820 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.2438. Min Act: -0.1700
Data Index: 472684 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.2438. Min Act: -0.1700
Data Index: 3193085 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.2125. Min Act: -0.1700
Data Index: 753318 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.1813. Min Act: -0.1700
Data Index: 2903203 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.1500. Min Act: -0.1700
Data Index: 1527449 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.1188. Min Act: -0.1700
Data Index: 889507 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.1188. Min Act: -0.1700
Data Index: 4095490 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.0563. Min Act: -0.1700
Data Index: 1964419 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.0250. Min Act: -0.1700
Data Index: 2507705 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9313. Min Range: -7.9313
Max Act: 7.0250. Min Act: -0.1700
Data Index: 2227209 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9313. Min Range: -7.9313
Max Act: 6.9938. Min Act: -0.1700
Data Index: 1014055 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19