Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2803 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4450. Min Range: -7.4450
Max Act: 7.4450. Min Act: -0.1700
Data Index: 4187651 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4450. Min Range: -7.4450
Max Act: 7.1950. Min Act: -0.1700
Data Index: 8752154 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4450. Min Range: -7.4450
Max Act: 7.1638. Min Act: -0.1700
Data Index: 5914513 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4450. Min Range: -7.4450
Max Act: 7.1950. Min Act: -0.1700
Data Index: 3152269 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4450. Min Range: -7.4450
Max Act: 7.0388. Min Act: -0.1700
Data Index: 4961013 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4450. Min Range: -7.4450
Max Act: 7.0388. Min Act: -0.1700
Data Index: 7662884 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4450. Min Range: -7.4450
Max Act: 7.0075. Min Act: -0.1700
Data Index: 4823094 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.9450. Min Act: -0.1700
Data Index: 5390921 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.9450. Min Act: -0.1700
Data Index: 6153993 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.9138. Min Act: -0.1700
Data Index: 6020599 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8825. Min Act: -0.1700
Data Index: 2856948 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8200. Min Act: -0.1700
Data Index: 3881831 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8513. Min Act: -0.1700
Data Index: 4244193 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8200. Min Act: -0.1700
Data Index: 8206176 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8513. Min Act: -0.1700
Data Index: 846587 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8200. Min Act: -0.1700
Data Index: 4738966 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.7888. Min Act: -0.1700
Data Index: 4736143 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.7888. Min Act: -0.1700
Data Index: 1614423 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8513. Min Act: -0.1700
Data Index: 1062338 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4450. Min Range: -7.4450
Max Act: 6.8200. Min Act: -0.1700
Data Index: 1474033 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #19