Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4427. Min Range: -6.4427
Max Act: 6.4427. Min Act: -0.1700
Data Index: 636103 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4427. Min Range: -6.4427
Max Act: 6.1615. Min Act: -0.1700
Data Index: 6922953 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4427. Min Range: -6.4427
Max Act: 6.0990. Min Act: -0.1700
Data Index: 7535599 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4427. Min Range: -6.4427
Max Act: 6.0677. Min Act: -0.1700
Data Index: 4165128 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4427. Min Range: -6.4427
Max Act: 6.0052. Min Act: -0.1700
Data Index: 1991528 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4427. Min Range: -6.4427
Max Act: 6.0052. Min Act: -0.1700
Data Index: 6474313 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9740. Min Act: -0.1700
Data Index: 3968977 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9740. Min Act: -0.1700
Data Index: 3060738 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9427. Min Act: -0.1700
Data Index: 6255713 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9427. Min Act: -0.1700
Data Index: 3468666 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9115. Min Act: -0.1700
Data Index: 3193550 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9115. Min Act: -0.1700
Data Index: 7294432 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9115. Min Act: -0.1700
Data Index: 831061 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9115. Min Act: -0.1700
Data Index: 182851 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.8802. Min Act: -0.1700
Data Index: 3803418 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.9115. Min Act: -0.1700
Data Index: 7505175 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.8490. Min Act: -0.1700
Data Index: 2273549 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.8490. Min Act: -0.1700
Data Index: 8360735 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.7865. Min Act: -0.1700
Data Index: 494500 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4427. Min Range: -6.4427
Max Act: 5.8177. Min Act: -0.1700
Data Index: 5641677 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19