Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2701 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.3812. Min Act: -0.1700
Data Index: 1796808 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.3187. Min Act: -0.1700
Data Index: 1934572 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.3500. Min Act: -0.1700
Data Index: 452535 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.3187. Min Act: -0.1700
Data Index: 2881895 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2875. Min Act: -0.1700
Data Index: 4740976 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2562. Min Act: -0.1700
Data Index: 1954714 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2875. Min Act: -0.1700
Data Index: 452534 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2875. Min Act: -0.1700
Data Index: 1423049 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2562. Min Act: -0.1700
Data Index: 2756331 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2250. Min Act: -0.1700
Data Index: 2002262 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2562. Min Act: -0.1700
Data Index: 8164010 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2250. Min Act: -0.1700
Data Index: 5523793 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.2250. Min Act: -0.1700
Data Index: 853796 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.1937. Min Act: -0.1700
Data Index: 4659218 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.1937. Min Act: -0.1700
Data Index: 4741890 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.1625. Min Act: -0.1700
Data Index: 2269317 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.1625. Min Act: -0.1700
Data Index: 5488774 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.1625. Min Act: -0.1700
Data Index: 4755643 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.1625. Min Act: -0.1700
Data Index: 7866797 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3812. Min Range: -4.3812
Max Act: 4.1312. Min Act: -0.1700
Data Index: 6115769 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19