Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2517 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.7349. Min Act: -0.1700
Data Index: 4849997 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.7662. Min Act: -0.1700
Data Index: 407612 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6724. Min Act: -0.1700
Data Index: 7042572 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.6412. Min Act: -0.1700
Data Index: 8631289 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5787. Min Act: -0.1700
Data Index: 3837108 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5474. Min Act: -0.1700
Data Index: 2247813 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5787. Min Act: -0.1700
Data Index: 2763855 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5474. Min Act: -0.1700
Data Index: 152669 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4849. Min Act: -0.1700
Data Index: 8597724 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5162. Min Act: -0.1700
Data Index: 4427596 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5162. Min Act: -0.1700
Data Index: 2088546 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.5162. Min Act: -0.1700
Data Index: 1744983 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4849. Min Act: -0.1700
Data Index: 8352680 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4849. Min Act: -0.1700
Data Index: 3100653 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4537. Min Act: -0.1700
Data Index: 4930410 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 2135905 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 4987961 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.4224. Min Act: -0.1700
Data Index: 460567 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3599. Min Act: -0.1700
Data Index: 8268655 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7662. Min Range: -5.7662
Max Act: 5.3599. Min Act: -0.1700
Data Index: 8341690 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19