Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1974 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1639. Min Range: -6.1639
Max Act: 6.1639. Min Act: -0.1675
Data Index: 5839236 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1639. Min Range: -6.1639
Max Act: 6.0076. Min Act: -0.1700
Data Index: 877228 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.9139. Min Act: -0.1700
Data Index: 1146952 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.8514. Min Act: -0.1700
Data Index: 8328925 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.7576. Min Act: -0.1700
Data Index: 3234493 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.7264. Min Act: -0.1700
Data Index: 7939583 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.6951. Min Act: -0.1700
Data Index: 2815266 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.6951. Min Act: -0.1391
Data Index: 51828 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.6639. Min Act: -0.1699
Data Index: 1591346 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.6014. Min Act: -0.1700
Data Index: 1244254 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.6014. Min Act: -0.1700
Data Index: 51832 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.5701. Min Act: -0.1700
Data Index: 504606 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.5389. Min Act: -0.1700
Data Index: 4215599 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.5076. Min Act: -0.1700
Data Index: 8341738 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.5076. Min Act: -0.1700
Data Index: 4240294 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.5076. Min Act: -0.1700
Data Index: 6938590 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.5076. Min Act: -0.1700
Data Index: 5215813 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.4764. Min Act: -0.1683
Data Index: 748608 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.5076. Min Act: -0.1700
Data Index: 2725025 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1639. Min Range: -6.1639
Max Act: 5.4764. Min Act: -0.1603
Data Index: 7107939 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19