Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2385 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.7931. Min Act: -0.1700
Data Index: 5926524 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.6681. Min Act: -0.1700
Data Index: 8476805 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.5431. Min Act: -0.1700
Data Index: 548211 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.4181. Min Act: -0.1700
Data Index: 5926523 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.4806. Min Act: -0.1700
Data Index: 1408090 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.4181. Min Act: -0.1700
Data Index: 954888 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.3556. Min Act: -0.1700
Data Index: 138079 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.3556. Min Act: -0.1700
Data Index: 2007934 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.2306. Min Act: -0.1700
Data Index: 6757124 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.2306. Min Act: -0.1700
Data Index: 4262076 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.2306. Min Act: -0.1700
Data Index: 1754579 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.2306. Min Act: -0.1700
Data Index: 2886885 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.0431. Min Act: -0.1700
Data Index: 6509373 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.1056. Min Act: -0.1700
Data Index: 2540286 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.1681. Min Act: -0.1700
Data Index: 7271389 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.1056. Min Act: -0.1700
Data Index: 4211365 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.0431. Min Act: -0.1700
Data Index: 1545997 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.0431. Min Act: -0.1700
Data Index: 1992054 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.0431. Min Act: -0.1700
Data Index: 2229151 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7931. Min Range: -8.7931
Max Act: 8.0431. Min Act: -0.1700
Data Index: 3035004 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19