Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1860 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.4094. Min Act: -0.1700
Data Index: 1570387 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.3156. Min Act: -0.1700
Data Index: 803835 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.2844. Min Act: -0.1700
Data Index: 202332 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.2219. Min Act: -0.1700
Data Index: 2699844 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.1906. Min Act: -0.1700
Data Index: 5037494 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0969. Min Act: -0.1700
Data Index: 1858378 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0656. Min Act: -0.1700
Data Index: 8022248 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0969. Min Act: -0.1700
Data Index: 346225 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0656. Min Act: -0.1700
Data Index: 3997965 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0969. Min Act: -0.1700
Data Index: 2639179 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0656. Min Act: -0.1700
Data Index: 8435109 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0031. Min Act: -0.1700
Data Index: 8535958 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0344. Min Act: -0.1700
Data Index: 6265855 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0344. Min Act: -0.1700
Data Index: 4934128 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0344. Min Act: -0.1700
Data Index: 7334144 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0031. Min Act: -0.1700
Data Index: 4903230 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0031. Min Act: -0.1700
Data Index: 8063686 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0344. Min Act: -0.1700
Data Index: 1545591 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4094. Min Range: -6.4094
Max Act: 6.0344. Min Act: -0.1700
Data Index: 1930658 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4094. Min Range: -6.4094
Max Act: 5.9719. Min Act: -0.1700
Data Index: 7811608 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19