Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.4372. Min Act: -0.1700
Data Index: 7714794 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.3434. Min Act: -0.1700
Data Index: 4609681 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.3122. Min Act: -0.1700
Data Index: 1329419 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.2497. Min Act: -0.1700
Data Index: 3360229 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.2497. Min Act: -0.1700
Data Index: 7789065 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.2184. Min Act: -0.1700
Data Index: 4719817 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1872. Min Act: -0.1700
Data Index: 3628727 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1872. Min Act: -0.1700
Data Index: 6473565 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.2184. Min Act: -0.1700
Data Index: 3768180 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1872. Min Act: -0.1700
Data Index: 4059555 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.2184. Min Act: -0.1700
Data Index: 6629016 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1872. Min Act: -0.1700
Data Index: 4719816 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.2184. Min Act: -0.1700
Data Index: 5689569 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1559. Min Act: -0.1700
Data Index: 139289 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1872. Min Act: -0.1700
Data Index: 7033228 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1559. Min Act: -0.1700
Data Index: 2659386 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1872. Min Act: -0.1700
Data Index: 6473562 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1559. Min Act: -0.1700
Data Index: 252511 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1559. Min Act: -0.1700
Data Index: 6446441 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4372. Min Range: -4.4372
Max Act: 4.1559. Min Act: -0.1700
Data Index: 2863678 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19