Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3375. Min Range: -7.3375
Max Act: 7.3375. Min Act: -0.1700
Data Index: 7240404 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3375. Min Range: -7.3375
Max Act: 7.1500. Min Act: -0.1700
Data Index: 3856855 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.9625. Min Act: -0.1700
Data Index: 980397 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.9625. Min Act: -0.1700
Data Index: 491643 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.9313. Min Act: -0.1700
Data Index: 8207294 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.9000. Min Act: -0.1700
Data Index: 1146033 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.8688. Min Act: -0.1700
Data Index: 487143 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.8375. Min Act: -0.1700
Data Index: 8622992 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.7125. Min Act: -0.1700
Data Index: 7181840 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.7125. Min Act: -0.1700
Data Index: 6606741 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6813. Min Act: -0.1700
Data Index: 4786782 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6500. Min Act: -0.1700
Data Index: 7819262 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6500. Min Act: -0.1700
Data Index: 4440265 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6500. Min Act: -0.1700
Data Index: 5255783 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6500. Min Act: -0.1700
Data Index: 41999 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6500. Min Act: -0.1700
Data Index: 8671888 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6188. Min Act: -0.1700
Data Index: 3086034 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.6188. Min Act: -0.1700
Data Index: 6734576 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.5875. Min Act: -0.1700
Data Index: 3826044 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3375. Min Range: -7.3375
Max Act: 6.5875. Min Act: -0.1700
Data Index: 7695827 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19