Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2892 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3697. Min Range: -6.3697
Max Act: 6.3697. Min Act: -0.1700
Data Index: 1530210 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3697. Min Range: -6.3697
Max Act: 6.1822. Min Act: -0.1700
Data Index: 1447525 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3697. Min Range: -6.3697
Max Act: 6.1822. Min Act: -0.1700
Data Index: 873084 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3697. Min Range: -6.3697
Max Act: 6.0885. Min Act: -0.1700
Data Index: 4626163 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9947. Min Act: -0.1700
Data Index: 3088232 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3697. Min Range: -6.3697
Max Act: 6.0260. Min Act: -0.1700
Data Index: 3028521 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3697. Min Range: -6.3697
Max Act: 6.0260. Min Act: -0.1700
Data Index: 1036933 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9635. Min Act: -0.1700
Data Index: 3486437 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9322. Min Act: -0.1700
Data Index: 997758 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9947. Min Act: -0.1700
Data Index: 6627002 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9010. Min Act: -0.1700
Data Index: 7992947 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9322. Min Act: -0.1700
Data Index: 8376380 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9635. Min Act: -0.1700
Data Index: 6784737 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9322. Min Act: -0.1700
Data Index: 544207 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.8697. Min Act: -0.1700
Data Index: 2579368 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9322. Min Act: -0.1700
Data Index: 3237742 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9010. Min Act: -0.1700
Data Index: 4120762 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.9322. Min Act: -0.1700
Data Index: 8308901 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.8697. Min Act: -0.1700
Data Index: 2609497 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3697. Min Range: -6.3697
Max Act: 5.8385. Min Act: -0.1700
Data Index: 8134353 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19