Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 15 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.7176. Min Act: -0.1700
Data Index: 8407008 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.4676. Min Act: -0.1700
Data Index: 8412221 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.4051. Min Act: -0.1700
Data Index: 3813258 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.4364. Min Act: -0.1700
Data Index: 73981 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.4051. Min Act: -0.1700
Data Index: 4912344 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3739. Min Act: -0.1700
Data Index: 2046216 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3739. Min Act: -0.1700
Data Index: 2608907 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3426. Min Act: -0.1700
Data Index: 2178301 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3426. Min Act: -0.1700
Data Index: 5923438 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3426. Min Act: -0.1700
Data Index: 6123479 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3114. Min Act: -0.1700
Data Index: 313637 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.2801. Min Act: -0.1700
Data Index: 4096141 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3114. Min Act: -0.1700
Data Index: 3637778 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.2801. Min Act: -0.1700
Data Index: 118118 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.2801. Min Act: -0.1700
Data Index: 602386 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.2801. Min Act: -0.1700
Data Index: 4697212 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.3114. Min Act: -0.1700
Data Index: 8355545 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.2489. Min Act: -0.1700
Data Index: 2872628 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.2801. Min Act: -0.1700
Data Index: 3414792 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7176. Min Range: -5.7176
Max Act: 5.1864. Min Act: -0.1700
Data Index: 904639 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19