Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5621 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.2220. Min Act: -0.1700
Data Index: 1977017 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.2220. Min Act: -0.1700
Data Index: 4142154 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.1908. Min Act: -0.1700
Data Index: 1385174 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.1283. Min Act: -0.1700
Data Index: 4086818 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0970. Min Act: -0.1700
Data Index: 6357238 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0658. Min Act: -0.1700
Data Index: 2733273 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0658. Min Act: -0.1700
Data Index: 4778695 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0658. Min Act: -0.1700
Data Index: 8577731 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0658. Min Act: -0.1700
Data Index: 8694270 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 147395 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 177603 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 3823785 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 147394 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0345. Min Act: -0.1700
Data Index: 4739612 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0033. Min Act: -0.1700
Data Index: 827685 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0033. Min Act: -0.1700
Data Index: 8340185 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0033. Min Act: -0.1700
Data Index: 1873457 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0033. Min Act: -0.1700
Data Index: 191615 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2220. Min Range: -5.2220
Max Act: 5.0033. Min Act: -0.1700
Data Index: 955421 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2220. Min Range: -5.2220
Max Act: 4.9408. Min Act: -0.1700
Data Index: 2597173 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19