Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3742 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.1298. Min Act: -0.1700
Data Index: 1112797 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.1298. Min Act: -0.1699
Data Index: 3520354 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.1298. Min Act: -0.1700
Data Index: 425909 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.1131. Min Act: -0.1700
Data Index: 6652850 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0964. Min Act: -0.1699
Data Index: 3436052 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.1131. Min Act: -0.1700
Data Index: 4590317 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0964. Min Act: -0.1700
Data Index: 4559619 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0964. Min Act: -0.1700
Data Index: 7838949 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0796. Min Act: -0.1700
Data Index: 1826133 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0628. Min Act: -0.1700
Data Index: 630593 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0796. Min Act: -0.1699
Data Index: 4753310 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0796. Min Act: -0.1700
Data Index: 2246677 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0796. Min Act: -0.1700
Data Index: 6908635 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0628. Min Act: -0.1700
Data Index: 6171740 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0628. Min Act: -0.1700
Data Index: 630592 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0628. Min Act: -0.1699
Data Index: 3332720 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0460. Min Act: -0.1700
Data Index: 4437431 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0460. Min Act: -0.1699
Data Index: 8408741 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0291. Min Act: -0.1700
Data Index: 4647219 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1298. Min Range: -2.1298
Max Act: 2.0291. Min Act: -0.1696
Data Index: 990424 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19