Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6108 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.2115. Min Act: -0.1700
Data Index: 4183529 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.2115. Min Act: -0.1700
Data Index: 7453895 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2115. Min Range: -5.2115
Max Act: 5.1803. Min Act: -0.1700
Data Index: 2884484 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.9615. Min Act: -0.1700
Data Index: 7249739 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.9303. Min Act: -0.1700
Data Index: 6591681 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8678. Min Act: -0.1700
Data Index: 6774465 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8678. Min Act: -0.1700
Data Index: 3815702 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8365. Min Act: -0.1700
Data Index: 2305696 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8365. Min Act: -0.1700
Data Index: 5597276 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8365. Min Act: -0.1700
Data Index: 6132714 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.8053. Min Act: -0.1700
Data Index: 5532525 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 508948 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 368384 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 8725514 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 6836955 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 4241910 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7428. Min Act: -0.1700
Data Index: 5906066 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7740. Min Act: -0.1700
Data Index: 1688530 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7428. Min Act: -0.1700
Data Index: 583682 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2115. Min Range: -5.2115
Max Act: 4.7428. Min Act: -0.1700
Data Index: 3428494 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19