Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5011 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.4303. Min Act: -0.1700
Data Index: 316609 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.3991. Min Act: -0.1695
Data Index: 5551585 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.3366. Min Act: -0.1700
Data Index: 2276464 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.3053. Min Act: -0.1699
Data Index: 671625 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.3053. Min Act: -0.1700
Data Index: 5053377 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2741. Min Act: -0.1698
Data Index: 3392738 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2741. Min Act: -0.1700
Data Index: 8538503 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2741. Min Act: -0.1700
Data Index: 1747155 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.3053. Min Act: -0.1700
Data Index: 3822128 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1700
Data Index: 4687900 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1699
Data Index: 7089265 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1696
Data Index: 2051299 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1699
Data Index: 7108458 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1692
Data Index: 7358195 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1700
Data Index: 2118743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1693
Data Index: 4967292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1700
Data Index: 1729375 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1700
Data Index: 4873401 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2116. Min Act: -0.1700
Data Index: 277463 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4303. Min Range: -5.4303
Max Act: 5.2428. Min Act: -0.1699
Data Index: 2134480 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19