Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.1515. Min Act: -0.1700
Data Index: 4839793 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.1203. Min Act: -0.1699
Data Index: 6724260 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.0578. Min Act: -0.1700
Data Index: 3993073 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 4620466 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 5455564 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.0578. Min Act: -0.1700
Data Index: 3909943 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 2453891 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9953. Min Act: -0.1700
Data Index: 7338269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9953. Min Act: -0.1699
Data Index: 767437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1515. Min Range: -5.1515
Max Act: 5.0265. Min Act: -0.1700
Data Index: 6164834 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9640. Min Act: -0.1700
Data Index: 4453406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9953. Min Act: -0.1700
Data Index: 704094 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9640. Min Act: -0.1700
Data Index: 7775190 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9328. Min Act: -0.1700
Data Index: 5891190 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9328. Min Act: -0.1700
Data Index: 8153441 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9328. Min Act: -0.1700
Data Index: 1811133 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9328. Min Act: -0.1700
Data Index: 3541529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9328. Min Act: -0.1700
Data Index: 7382611 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9328. Min Act: -0.1700
Data Index: 2547588 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1515. Min Range: -5.1515
Max Act: 4.9328. Min Act: -0.1697
Data Index: 1886996 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19