Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 919 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1278. Min Range: -5.1278
Max Act: 5.1278. Min Act: -0.1700
Data Index: 54750 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.9403. Min Act: -0.1700
Data Index: 1052569 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8778. Min Act: -0.1700
Data Index: 3606523 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.8153. Min Act: -0.1700
Data Index: 993803 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.7528. Min Act: -0.1700
Data Index: 842697 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.7528. Min Act: -0.1700
Data Index: 1226295 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.7528. Min Act: -0.1700
Data Index: 8711733 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.6903. Min Act: -0.1700
Data Index: 6332536 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.6903. Min Act: -0.1700
Data Index: 7827463 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.6590. Min Act: -0.1700
Data Index: 7072081 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5965. Min Act: -0.1700
Data Index: 7611463 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5965. Min Act: -0.1700
Data Index: 3585073 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5965. Min Act: -0.1700
Data Index: 777550 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5340. Min Act: -0.1700
Data Index: 4870488 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5965. Min Act: -0.1700
Data Index: 6332535 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5653. Min Act: -0.1700
Data Index: 3966313 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5340. Min Act: -0.1700
Data Index: 2521184 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5340. Min Act: -0.1700
Data Index: 2205806 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5653. Min Act: -0.1700
Data Index: 1144754 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1278. Min Range: -5.1278
Max Act: 4.5340. Min Act: -0.1700
Data Index: 8122491 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19