Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2076 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2357. Min Range: -4.2357
Max Act: 4.2357. Min Act: -0.1700
Data Index: 4733553 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2357. Min Range: -4.2357
Max Act: 4.0794. Min Act: -0.1700
Data Index: 8012843 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2357. Min Range: -4.2357
Max Act: 4.0169. Min Act: -0.1700
Data Index: 6200180 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2357. Min Range: -4.2357
Max Act: 4.0169. Min Act: -0.1700
Data Index: 1780530 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.9856. Min Act: -0.1700
Data Index: 2419011 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.9856. Min Act: -0.1700
Data Index: 98614 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.9544. Min Act: -0.1700
Data Index: 6139184 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.9544. Min Act: -0.1700
Data Index: 1624099 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.9231. Min Act: -0.1700
Data Index: 7615945 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.8293. Min Act: -0.1700
Data Index: 3420321 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.8293. Min Act: -0.1700
Data Index: 2708095 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.8293. Min Act: -0.1700
Data Index: 4197880 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.7980. Min Act: -0.1700
Data Index: 4795565 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.7667. Min Act: -0.1700
Data Index: 2823161 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.7667. Min Act: -0.1700
Data Index: 2483462 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.7355. Min Act: -0.1700
Data Index: 6350492 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.7042. Min Act: -0.1700
Data Index: 7387694 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.7042. Min Act: -0.1700
Data Index: 7671834 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.7042. Min Act: -0.1700
Data Index: 5362264 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2357. Min Range: -4.2357
Max Act: 3.6416. Min Act: -0.1700
Data Index: 1601417 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19