Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5742 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0208. Min Range: -6.0208
Max Act: 6.0208. Min Act: -0.1700
Data Index: 2625034 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0208. Min Range: -6.0208
Max Act: 6.0208. Min Act: -0.1700
Data Index: 8229656 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9895. Min Act: -0.1700
Data Index: 6671109 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9895. Min Act: -0.1700
Data Index: 3802876 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9895. Min Act: -0.1700
Data Index: 8681605 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9270. Min Act: -0.1700
Data Index: 3291752 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9583. Min Act: -0.1700
Data Index: 6008614 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9583. Min Act: -0.1700
Data Index: 3364706 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9270. Min Act: -0.1700
Data Index: 5525076 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9270. Min Act: -0.1700
Data Index: 6478800 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9583. Min Act: -0.1700
Data Index: 666356 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.9270. Min Act: -0.1700
Data Index: 470841 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 5174286 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 3591392 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 2851968 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 4747141 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 3463382 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 6870048 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8958. Min Act: -0.1700
Data Index: 5701835 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0208. Min Range: -6.0208
Max Act: 5.8645. Min Act: -0.1700
Data Index: 3699913 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19