Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.8215. Min Act: -0.1700
Data Index: 1171368 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 8254476 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 2958714 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 6367587 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 2543382 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 5973228 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 5713424 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 5421241 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 138007 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7902. Min Act: -0.1700
Data Index: 3954160 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 5691446 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 2226728 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 1278211 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 2543383 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 1773098 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 2793878 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 6945684 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 3118190 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 7479239 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8215. Min Range: -3.8215
Max Act: 3.7589. Min Act: -0.1700
Data Index: 7527763 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19