Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.4632. Min Act: -0.1700
Data Index: 6687669 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.4144. Min Act: -0.1700
Data Index: 5976402 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.3162. Min Act: -0.1700
Data Index: 3271172 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.3162. Min Act: -0.1700
Data Index: 7290504 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2997. Min Act: -0.1699
Data Index: 6173938 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2833. Min Act: -0.1700
Data Index: 5487482 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2997. Min Act: -0.1700
Data Index: 99214 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2833. Min Act: -0.1699
Data Index: 6742920 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2503. Min Act: -0.1700
Data Index: 2685987 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2668. Min Act: -0.1699
Data Index: 8137369 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2503. Min Act: -0.1700
Data Index: 4529561 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2337. Min Act: -0.1700
Data Index: 6103003 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2503. Min Act: -0.1700
Data Index: 1435157 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2668. Min Act: -0.1700
Data Index: 5050067 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2337. Min Act: -0.1700
Data Index: 6890057 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2337. Min Act: -0.1700
Data Index: 1715042 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2172. Min Act: -0.1700
Data Index: 7098542 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2006. Min Act: -0.1700
Data Index: 1066898 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2337. Min Act: -0.1700
Data Index: 6557600 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4632. Min Range: -2.4632
Max Act: 2.2337. Min Act: -0.1700
Data Index: 1046264 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19