Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.3743. Min Act: -0.1700
Data Index: 42919 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.3743. Min Act: -0.1700
Data Index: 5330921 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.3478. Min Act: -0.1700
Data Index: 4750376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.3037. Min Act: -0.1700
Data Index: 3364087 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.2332. Min Act: -0.1700
Data Index: 6555068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.2068. Min Act: -0.1700
Data Index: 1234430 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.1101. Min Act: -0.1700
Data Index: 4960579 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.1101. Min Act: -0.1700
Data Index: 7913476 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.0926. Min Act: -0.1700
Data Index: 5928113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.0751. Min Act: -0.1700
Data Index: 717714 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.0576. Min Act: -0.1700
Data Index: 4750374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3743. Min Range: -1.3743
Max Act: 1.0315. Min Act: -0.1700
Data Index: 8622402 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9621. Min Act: -0.1700
Data Index: 5741681 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9448. Min Act: -0.1700
Data Index: 5792279 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9621. Min Act: -0.1700
Data Index: 8438871 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9362. Min Act: -0.1700
Data Index: 8438882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9448. Min Act: -0.1700
Data Index: 3592468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9276. Min Act: -0.1700
Data Index: 5426672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9276. Min Act: -0.1700
Data Index: 6063561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3743. Min Range: -1.3743
Max Act: 0.9276. Min Act: -0.1700
Data Index: 1132068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19