Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.6053. Min Act: -0.1700
Data Index: 7030021 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.6053. Min Act: -0.1700
Data Index: 7643858 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.5741. Min Act: -0.1700
Data Index: 1376226 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.5116. Min Act: -0.1700
Data Index: 7797065 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.5428. Min Act: -0.1700
Data Index: 7031457 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.5116. Min Act: -0.1700
Data Index: 7777762 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4803. Min Act: -0.1700
Data Index: 7356795 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.5116. Min Act: -0.1700
Data Index: 3171948 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.5116. Min Act: -0.1700
Data Index: 2641902 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4491. Min Act: -0.1700
Data Index: 7350510 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4803. Min Act: -0.1700
Data Index: 416681 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4491. Min Act: -0.1700
Data Index: 3708757 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.4491. Min Act: -0.1700
Data Index: 4978157 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3553. Min Act: -0.1700
Data Index: 4938330 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3866. Min Act: -0.1700
Data Index: 3953076 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3866. Min Act: -0.1700
Data Index: 4035770 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3866. Min Act: -0.1700
Data Index: 8232815 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3553. Min Act: -0.1700
Data Index: 847263 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3553. Min Act: -0.1700
Data Index: 4615285 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6053. Min Range: -5.6053
Max Act: 5.3553. Min Act: -0.1700
Data Index: 7724211 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19