Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3419. Min Range: -6.3419
Max Act: 6.3419. Min Act: -0.1700
Data Index: 3309253 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3419. Min Range: -6.3419
Max Act: 6.1231. Min Act: -0.1700
Data Index: 8186037 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3419. Min Range: -6.3419
Max Act: 6.0919. Min Act: -0.1700
Data Index: 6752248 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3419. Min Range: -6.3419
Max Act: 6.0919. Min Act: -0.1700
Data Index: 5825080 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3419. Min Range: -6.3419
Max Act: 6.0294. Min Act: -0.1700
Data Index: 6910473 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.9981. Min Act: -0.1700
Data Index: 3933998 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.9356. Min Act: -0.1700
Data Index: 4139960 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.9044. Min Act: -0.1700
Data Index: 7650999 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.9044. Min Act: -0.1700
Data Index: 5446050 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.9044. Min Act: -0.1700
Data Index: 7498750 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8731. Min Act: -0.1700
Data Index: 795460 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8731. Min Act: -0.1700
Data Index: 4109501 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8731. Min Act: -0.1700
Data Index: 3200208 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8419. Min Act: -0.1700
Data Index: 1100891 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8419. Min Act: -0.1700
Data Index: 8354123 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8419. Min Act: -0.1700
Data Index: 8016645 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8106. Min Act: -0.1700
Data Index: 1724697 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8106. Min Act: -0.1700
Data Index: 4519098 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8106. Min Act: -0.1700
Data Index: 1704283 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3419. Min Range: -6.3419
Max Act: 5.8106. Min Act: -0.1700
Data Index: 6215945 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19