Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.3176. Min Act: -0.1700
Data Index: 408433 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.1926. Min Act: -0.1700
Data Index: 1237330 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.1301. Min Act: -0.1700
Data Index: 1228159 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.0676. Min Act: -0.1700
Data Index: 670632 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.0363. Min Act: -0.1700
Data Index: 3273095 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.0363. Min Act: -0.1700
Data Index: 8721009 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.0363. Min Act: -0.1700
Data Index: 4845815 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.0363. Min Act: -0.1700
Data Index: 6703750 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.0051. Min Act: -0.1700
Data Index: 5567046 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3176. Min Range: -4.3176
Max Act: 4.0363. Min Act: -0.1700
Data Index: 4505579 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9738. Min Act: -0.1700
Data Index: 5073764 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9425. Min Act: -0.1700
Data Index: 6275493 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9425. Min Act: -0.1700
Data Index: 6893185 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9738. Min Act: -0.1700
Data Index: 3107013 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9738. Min Act: -0.1700
Data Index: 6521757 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9738. Min Act: -0.1700
Data Index: 5968194 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9738. Min Act: -0.1700
Data Index: 8145150 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9738. Min Act: -0.1700
Data Index: 3566367 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9425. Min Act: -0.1700
Data Index: 7962595 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3176. Min Range: -4.3176
Max Act: 3.9425. Min Act: -0.1700
Data Index: 7225461 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19