Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4518. Min Range: -8.4518
Max Act: 8.4518. Min Act: -0.1700
Data Index: 7807890 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4518. Min Range: -8.4518
Max Act: 8.3268. Min Act: -0.1700
Data Index: 6313787 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4518. Min Range: -8.4518
Max Act: 8.2018. Min Act: -0.1700
Data Index: 4051069 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4518. Min Range: -8.4518
Max Act: 8.0143. Min Act: -0.1700
Data Index: 6125657 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.9518. Min Act: -0.1700
Data Index: 7707509 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.9518. Min Act: -0.1700
Data Index: 7011808 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.9206. Min Act: -0.1700
Data Index: 1966348 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.9206. Min Act: -0.1700
Data Index: 3761004 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.8893. Min Act: -0.1700
Data Index: 80654 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.8893. Min Act: -0.1700
Data Index: 4587085 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.8893. Min Act: -0.1700
Data Index: 1364688 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.8893. Min Act: -0.1700
Data Index: 6864280 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.8268. Min Act: -0.1700
Data Index: 5607220 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.7643. Min Act: -0.1700
Data Index: 6422531 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.7643. Min Act: -0.1700
Data Index: 7055020 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.7643. Min Act: -0.1700
Data Index: 5613410 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.7331. Min Act: -0.1700
Data Index: 6486598 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.7018. Min Act: -0.1700
Data Index: 8539788 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.7018. Min Act: -0.1700
Data Index: 1745198 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4518. Min Range: -8.4518
Max Act: 7.6706. Min Act: -0.1700
Data Index: 4304960 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19