Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 85 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3049. Min Range: -6.3049
Max Act: 6.3049. Min Act: -0.1700
Data Index: 7480123 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.9299. Min Act: -0.1700
Data Index: 3894082 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.9299. Min Act: -0.1700
Data Index: 4468910 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.8361. Min Act: -0.1700
Data Index: 1789389 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.8361. Min Act: -0.1700
Data Index: 1350728 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.8049. Min Act: -0.1700
Data Index: 1993799 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.8049. Min Act: -0.1700
Data Index: 2428431 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.7736. Min Act: -0.1700
Data Index: 6976111 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.7736. Min Act: -0.1700
Data Index: 2569122 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.7111. Min Act: -0.1700
Data Index: 2585254 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.7424. Min Act: -0.1700
Data Index: 4373162 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.7111. Min Act: -0.1700
Data Index: 7448682 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.7111. Min Act: -0.1700
Data Index: 4804337 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.6799. Min Act: -0.1700
Data Index: 6793807 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.6799. Min Act: -0.1700
Data Index: 3885868 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.6799. Min Act: -0.1700
Data Index: 6667370 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.6486. Min Act: -0.1700
Data Index: 7501287 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.6486. Min Act: -0.1700
Data Index: 8202053 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.6486. Min Act: -0.1700
Data Index: 2432482 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3049. Min Range: -6.3049
Max Act: 5.6174. Min Act: -0.1700
Data Index: 1657228 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19