Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.1087. Min Act: -0.1700
Data Index: 603270 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.1087. Min Act: -0.1700
Data Index: 3681859 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0929. Min Act: -0.1700
Data Index: 5288415 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0456. Min Act: -0.1700
Data Index: 5955763 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0298. Min Act: -0.1700
Data Index: 6507098 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0298. Min Act: -0.1700
Data Index: 2020272 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0298. Min Act: -0.1700
Data Index: 6304099 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0140. Min Act: -0.1700
Data Index: 3663657 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0456. Min Act: -0.1700
Data Index: 7549255 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0298. Min Act: -0.1700
Data Index: 5544012 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0298. Min Act: -0.1700
Data Index: 1815377 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0298. Min Act: -0.1700
Data Index: 3941314 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0140. Min Act: -0.1700
Data Index: 1782852 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1087. Min Range: -3.1087
Max Act: 2.9982. Min Act: -0.1700
Data Index: 4771695 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1087. Min Range: -3.1087
Max Act: 3.0140. Min Act: -0.1700
Data Index: 7048577 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1087. Min Range: -3.1087
Max Act: 2.9982. Min Act: -0.1700
Data Index: 928638 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1087. Min Range: -3.1087
Max Act: 2.9824. Min Act: -0.1700
Data Index: 5588140 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1087. Min Range: -3.1087
Max Act: 2.9982. Min Act: -0.1700
Data Index: 1868806 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1087. Min Range: -3.1087
Max Act: 2.9982. Min Act: -0.1700
Data Index: 4548802 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1087. Min Range: -3.1087
Max Act: 2.9982. Min Act: -0.1700
Data Index: 5848624 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19