Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3774 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.5112. Min Act: -0.1700
Data Index: 5498873 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.3237. Min Act: -0.1700
Data Index: 6084437 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.2612. Min Act: -0.1700
Data Index: 4406100 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.2300. Min Act: -0.1700
Data Index: 7462118 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.2300. Min Act: -0.1700
Data Index: 5498862 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.2300. Min Act: -0.1700
Data Index: 8614576 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1987. Min Act: -0.1700
Data Index: 3159931 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1987. Min Act: -0.1700
Data Index: 4628540 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1362. Min Act: -0.1700
Data Index: 8407650 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1362. Min Act: -0.1700
Data Index: 1761590 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1675. Min Act: -0.1700
Data Index: 3457806 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1050. Min Act: -0.1700
Data Index: 6720426 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1362. Min Act: -0.1700
Data Index: 7682172 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1362. Min Act: -0.1700
Data Index: 5552697 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1675. Min Act: -0.1700
Data Index: 8298281 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1362. Min Act: -0.1700
Data Index: 8675441 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1050. Min Act: -0.1700
Data Index: 7869816 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1050. Min Act: -0.1700
Data Index: 4940655 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.1362. Min Act: -0.1700
Data Index: 761969 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5112. Min Range: -5.5112
Max Act: 5.0425. Min Act: -0.1700
Data Index: 6074581 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19