Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6515. Min Act: -0.1700
Data Index: 5759930 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6202. Min Act: -0.1700
Data Index: 2892981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6202. Min Act: -0.1700
Data Index: 307280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6202. Min Act: -0.1700
Data Index: 1478992 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.6202. Min Act: -0.1700
Data Index: 4549666 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 6803600 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 2506078 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 7344569 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 29535 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 4443458 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 1690092 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 97559 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5889. Min Act: -0.1700
Data Index: 3710361 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5576. Min Act: -0.1700
Data Index: 2737090 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5576. Min Act: -0.1700
Data Index: 2824509 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5576. Min Act: -0.1700
Data Index: 3053196 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5576. Min Act: -0.1700
Data Index: 3068252 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5576. Min Act: -0.1700
Data Index: 3338531 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5576. Min Act: -0.1700
Data Index: 293290 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6515. Min Range: -3.6515
Max Act: 3.5576. Min Act: -0.1700
Data Index: 1489524 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19