Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2350 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.9976. Min Act: -0.1700
Data Index: 5410639 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.9664. Min Act: -0.1700
Data Index: 3412772 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.9351. Min Act: -0.1700
Data Index: 5295143 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.9664. Min Act: -0.1700
Data Index: 1741121 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.8101. Min Act: -0.1700
Data Index: 1672901 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7789. Min Act: -0.1700
Data Index: 4462420 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7789. Min Act: -0.1700
Data Index: 6638519 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7476. Min Act: -0.1700
Data Index: 1558817 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7476. Min Act: -0.1700
Data Index: 788070 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 2024978 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7789. Min Act: -0.1700
Data Index: 5657490 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7476. Min Act: -0.1700
Data Index: 5268346 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 1685023 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 3502180 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 4481435 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 5668811 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 3899801 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 3642820 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.7164. Min Act: -0.1700
Data Index: 5668812 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9976. Min Range: -4.9976
Max Act: 4.6851. Min Act: -0.1700
Data Index: 5398402 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19