Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 208 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.5997. Min Act: -0.1700
Data Index: 5364516 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.5372. Min Act: -0.1700
Data Index: 2728273 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4747. Min Act: -0.1700
Data Index: 2989664 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4122. Min Act: -0.1700
Data Index: 4821258 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4435. Min Act: -0.1700
Data Index: 6786604 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4122. Min Act: -0.1700
Data Index: 5444158 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4435. Min Act: -0.1700
Data Index: 7824157 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4122. Min Act: -0.1700
Data Index: 3724716 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4435. Min Act: -0.1700
Data Index: 4495906 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.4122. Min Act: -0.1700
Data Index: 2722012 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3497. Min Act: -0.1700
Data Index: 1534827 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3497. Min Act: -0.1700
Data Index: 8467379 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3810. Min Act: -0.1700
Data Index: 4058513 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3185. Min Act: -0.1700
Data Index: 5772502 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3185. Min Act: -0.1700
Data Index: 2343264 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3497. Min Act: -0.1700
Data Index: 4676399 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3497. Min Act: -0.1700
Data Index: 805804 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3497. Min Act: -0.1700
Data Index: 6171454 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3185. Min Act: -0.1700
Data Index: 7081439 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5997. Min Range: -4.5997
Max Act: 4.3497. Min Act: -0.1700
Data Index: 2219801 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19