Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2172 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4051. Min Range: -7.4051
Max Act: 7.3738. Min Act: -0.1700
Data Index: 2882776 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4051. Min Range: -7.4051
Max Act: 7.4051. Min Act: -0.1700
Data Index: 2118561 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4051. Min Range: -7.4051
Max Act: 7.1551. Min Act: -0.1700
Data Index: 7245728 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4051. Min Range: -7.4051
Max Act: 7.1238. Min Act: -0.1700
Data Index: 655548 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4051. Min Range: -7.4051
Max Act: 7.0926. Min Act: -0.1700
Data Index: 4327557 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.8113. Min Act: -0.1700
Data Index: 4003233 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.8113. Min Act: -0.1700
Data Index: 2255385 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7801. Min Act: -0.1700
Data Index: 4684067 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7801. Min Act: -0.1700
Data Index: 6785469 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7176. Min Act: -0.1700
Data Index: 8537450 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7176. Min Act: -0.1700
Data Index: 5261271 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7176. Min Act: -0.1700
Data Index: 1957542 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7176. Min Act: -0.1700
Data Index: 2573274 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7176. Min Act: -0.1700
Data Index: 4417853 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.7176. Min Act: -0.1700
Data Index: 6582593 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.6863. Min Act: -0.1700
Data Index: 5924541 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.6551. Min Act: -0.1700
Data Index: 483535 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.6551. Min Act: -0.1700
Data Index: 7511729 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.6551. Min Act: -0.1700
Data Index: 1561434 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4051. Min Range: -7.4051
Max Act: 6.6238. Min Act: -0.1700
Data Index: 5729421 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19