Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3865. Min Range: -6.3865
Max Act: 6.3865. Min Act: -0.1700
Data Index: 6555205 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3865. Min Range: -6.3865
Max Act: 6.2303. Min Act: -0.1700
Data Index: 6909096 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3865. Min Range: -6.3865
Max Act: 6.1365. Min Act: -0.1700
Data Index: 2005690 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3865. Min Range: -6.3865
Max Act: 6.0740. Min Act: -0.1700
Data Index: 7741371 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3865. Min Range: -6.3865
Max Act: 6.0115. Min Act: -0.1700
Data Index: 7924183 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.9803. Min Act: -0.1700
Data Index: 8001212 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.8865. Min Act: -0.1700
Data Index: 6779425 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.8553. Min Act: -0.1700
Data Index: 7131807 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.7928. Min Act: -0.1700
Data Index: 1590130 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.7615. Min Act: -0.1700
Data Index: 5882486 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.7615. Min Act: -0.1700
Data Index: 5894565 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6678. Min Act: -0.1700
Data Index: 4803565 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6678. Min Act: -0.1700
Data Index: 2005686 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6990. Min Act: -0.1700
Data Index: 6613791 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6678. Min Act: -0.1700
Data Index: 2005685 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6678. Min Act: -0.1700
Data Index: 2005687 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6365. Min Act: -0.1700
Data Index: 4992249 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6365. Min Act: -0.1700
Data Index: 2221777 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6365. Min Act: -0.1700
Data Index: 4437125 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3865. Min Range: -6.3865
Max Act: 5.6365. Min Act: -0.1700
Data Index: 6446250 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19