Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 30 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.4181. Min Act: -0.1700
Data Index: 6932526 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.3556. Min Act: -0.1700
Data Index: 3054856 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.3556. Min Act: -0.1700
Data Index: 498910 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.3244. Min Act: -0.1700
Data Index: 6767441 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.2619. Min Act: -0.1700
Data Index: 8481194 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1994. Min Act: -0.1700
Data Index: 6863009 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1994. Min Act: -0.1700
Data Index: 2670132 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1369. Min Act: -0.1700
Data Index: 7482716 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1369. Min Act: -0.1700
Data Index: 4913706 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1369. Min Act: -0.1700
Data Index: 8351924 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.1369. Min Act: -0.1700
Data Index: 1006937 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0744. Min Act: -0.1700
Data Index: 3936015 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0431. Min Act: -0.1700
Data Index: 1768962 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0744. Min Act: -0.1700
Data Index: 4937385 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0744. Min Act: -0.1700
Data Index: 996212 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0431. Min Act: -0.1700
Data Index: 7152713 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0744. Min Act: -0.1700
Data Index: 4916670 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0431. Min Act: -0.1700
Data Index: 4298736 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4181. Min Range: -5.4181
Max Act: 4.9806. Min Act: -0.1700
Data Index: 778450 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4181. Min Range: -5.4181
Max Act: 5.0119. Min Act: -0.1700
Data Index: 2119093 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19