Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4126 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.4546. Min Act: -0.1699
Data Index: 1583319 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.4546. Min Act: -0.1699
Data Index: 3049760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.3609. Min Act: -0.1699
Data Index: 5205600 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.3296. Min Act: -0.1699
Data Index: 577120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.3609. Min Act: -0.1700
Data Index: 5811391 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.3296. Min Act: -0.1700
Data Index: 494269 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2984. Min Act: -0.1700
Data Index: 6817308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2984. Min Act: -0.1700
Data Index: 4633965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2984. Min Act: -0.1700
Data Index: 4959554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2671. Min Act: -0.1687
Data Index: 4191051 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2359. Min Act: -0.1700
Data Index: 3813035 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2359. Min Act: -0.1700
Data Index: 5199185 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2671. Min Act: -0.1700
Data Index: 1749768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2046. Min Act: -0.1700
Data Index: 6604283 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2359. Min Act: -0.1696
Data Index: 7714880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2359. Min Act: -0.1700
Data Index: 3010351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2046. Min Act: -0.1700
Data Index: 4288464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2046. Min Act: -0.1699
Data Index: 6052260 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.2046. Min Act: -0.1700
Data Index: 3986686 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4546. Min Range: -5.4546
Max Act: 5.1734. Min Act: -0.1659
Data Index: 166014 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19