Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.5526. Min Act: -0.1700
Data Index: 8099722 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.3339. Min Act: -0.1700
Data Index: 646380 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.3651. Min Act: -0.1700
Data Index: 6123118 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.2089. Min Act: -0.1700
Data Index: 1265991 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1776. Min Act: -0.1700
Data Index: 6627361 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 225767 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1464. Min Act: -0.1700
Data Index: 4222104 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1151. Min Act: -0.1700
Data Index: 8788518 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.1151. Min Act: -0.1700
Data Index: 4671134 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.0839. Min Act: -0.1700
Data Index: 2890250 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.0839. Min Act: -0.1700
Data Index: 8426597 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.0214. Min Act: -0.1700
Data Index: 1667336 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5526. Min Range: -5.5526
Max Act: 5.0214. Min Act: -0.1700
Data Index: 7703064 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5526. Min Range: -5.5526
Max Act: 4.9901. Min Act: -0.1700
Data Index: 8628708 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5526. Min Range: -5.5526
Max Act: 4.9901. Min Act: -0.1700
Data Index: 3849699 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5526. Min Range: -5.5526
Max Act: 4.9589. Min Act: -0.1700
Data Index: 4671128 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5526. Min Range: -5.5526
Max Act: 4.9589. Min Act: -0.1700
Data Index: 2618293 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5526. Min Range: -5.5526
Max Act: 4.9589. Min Act: -0.1700
Data Index: 2059184 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5526. Min Range: -5.5526
Max Act: 4.9589. Min Act: -0.1700
Data Index: 3765097 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5526. Min Range: -5.5526
Max Act: 4.9276. Min Act: -0.1700
Data Index: 8574912 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19