Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4835 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.2199. Min Act: -0.1700
Data Index: 983986 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.1886. Min Act: -0.1700
Data Index: 2886679 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.1261. Min Act: -0.1700
Data Index: 8075514 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.1261. Min Act: -0.1700
Data Index: 4733426 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0636. Min Act: -0.1700
Data Index: 1024390 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0949. Min Act: -0.1700
Data Index: 1466149 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0949. Min Act: -0.1700
Data Index: 5463381 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0324. Min Act: -0.1700
Data Index: 6080197 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0636. Min Act: -0.1700
Data Index: 3979885 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0324. Min Act: -0.1700
Data Index: 1707276 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0324. Min Act: -0.1700
Data Index: 4857253 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0324. Min Act: -0.1700
Data Index: 7913639 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0324. Min Act: -0.1700
Data Index: 8194896 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0324. Min Act: -0.1700
Data Index: 2808503 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0011. Min Act: -0.1700
Data Index: 6302879 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0011. Min Act: -0.1700
Data Index: 4163226 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2199. Min Range: -5.2199
Max Act: 5.0011. Min Act: -0.1700
Data Index: 4036434 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2199. Min Range: -5.2199
Max Act: 4.9699. Min Act: -0.1700
Data Index: 2441522 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2199. Min Range: -5.2199
Max Act: 4.9386. Min Act: -0.1700
Data Index: 774435 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2199. Min Range: -5.2199
Max Act: 4.9699. Min Act: -0.1700
Data Index: 4856550 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19