Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0809. Min Act: -0.1700
Data Index: 629674 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0809. Min Range: -5.0809
Max Act: 5.0184. Min Act: -0.1700
Data Index: 7874543 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9871. Min Act: -0.1700
Data Index: 5175067 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9871. Min Act: -0.1700
Data Index: 7196135 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9246. Min Act: -0.1700
Data Index: 6549867 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9871. Min Act: -0.1700
Data Index: 3780165 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9246. Min Act: -0.1700
Data Index: 5638960 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9246. Min Act: -0.1700
Data Index: 3560577 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9246. Min Act: -0.1700
Data Index: 3147541 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.9246. Min Act: -0.1700
Data Index: 6998971 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8934. Min Act: -0.1700
Data Index: 300322 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8934. Min Act: -0.1700
Data Index: 7364723 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8934. Min Act: -0.1700
Data Index: 7192688 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8934. Min Act: -0.1700
Data Index: 1672619 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8934. Min Act: -0.1700
Data Index: 738561 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8934. Min Act: -0.1700
Data Index: 4750642 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8621. Min Act: -0.1700
Data Index: 1237115 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8621. Min Act: -0.1700
Data Index: 4131628 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8621. Min Act: -0.1700
Data Index: 2252861 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0809. Min Range: -5.0809
Max Act: 4.8621. Min Act: -0.1700
Data Index: 2577230 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19