Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4374 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.9755. Min Act: -0.1700
Data Index: 2524334 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.9755. Min Act: -0.1700
Data Index: 4668398 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.8818. Min Act: -0.1700
Data Index: 2648366 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.8818. Min Act: -0.1700
Data Index: 6847752 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.8818. Min Act: -0.1700
Data Index: 4525736 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.8505. Min Act: -0.1700
Data Index: 7329152 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.8193. Min Act: -0.1700
Data Index: 5881727 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7880. Min Act: -0.1700
Data Index: 1060716 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7880. Min Act: -0.1700
Data Index: 8220564 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7880. Min Act: -0.1700
Data Index: 1203050 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7880. Min Act: -0.1700
Data Index: 1056636 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7568. Min Act: -0.1700
Data Index: 291652 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7568. Min Act: -0.1700
Data Index: 1984493 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7568. Min Act: -0.1700
Data Index: 1580424 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.7255. Min Act: -0.1700
Data Index: 6825018 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.6943. Min Act: -0.1700
Data Index: 4578560 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.6943. Min Act: -0.1700
Data Index: 2177961 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.6943. Min Act: -0.1700
Data Index: 2821243 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.6943. Min Act: -0.1700
Data Index: 6352254 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.6943. Min Act: -0.1700
Data Index: 3123210 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19