Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 896 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.4694. Min Act: -0.1700
Data Index: 3945905 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.4694. Min Act: -0.1700
Data Index: 5013740 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.5007. Min Act: -0.1700
Data Index: 1674328 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.4694. Min Act: -0.1700
Data Index: 2875989 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.4694. Min Act: -0.1700
Data Index: 9501 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.4069. Min Act: -0.1700
Data Index: 5993077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3757. Min Act: -0.1700
Data Index: 8274267 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3757. Min Act: -0.1700
Data Index: 649749 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 4999748 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 914184 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 773415 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3444. Min Act: -0.1700
Data Index: 4817844 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 4650472 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 7870899 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 410371 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 8555473 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 5764553 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.3132. Min Act: -0.1700
Data Index: 5664205 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.2507. Min Act: -0.1700
Data Index: 3700978 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5007. Min Range: -4.5007
Max Act: 4.2819. Min Act: -0.1700
Data Index: 7153548 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19