Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2875 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.8516. Min Act: -0.1700
Data Index: 5359822 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.8360. Min Act: -0.1700
Data Index: 2706266 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.8047. Min Act: -0.1700
Data Index: 2102106 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7265. Min Act: -0.1700
Data Index: 4324756 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7109. Min Act: -0.1700
Data Index: 7410326 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7265. Min Act: -0.1700
Data Index: 7473478 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7265. Min Act: -0.1700
Data Index: 8794161 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7265. Min Act: -0.1700
Data Index: 4380 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7109. Min Act: -0.1700
Data Index: 2814073 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7109. Min Act: -0.1700
Data Index: 6802719 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.7265. Min Act: -0.1700
Data Index: 2226166 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6796. Min Act: -0.1700
Data Index: 5627446 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6952. Min Act: -0.1700
Data Index: 2796510 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6639. Min Act: -0.1700
Data Index: 5728632 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6796. Min Act: -0.1700
Data Index: 1450645 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6796. Min Act: -0.1700
Data Index: 4103755 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6483. Min Act: -0.1700
Data Index: 6607032 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6639. Min Act: -0.1700
Data Index: 3970199 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6483. Min Act: -0.1700
Data Index: 3900892 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8516. Min Range: -3.8516
Max Act: 3.6483. Min Act: -0.1700
Data Index: 6007691 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19