Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1243. Min Range: -4.1243
Max Act: 4.1243. Min Act: -0.1700
Data Index: 4475991 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1243. Min Range: -4.1243
Max Act: 4.0617. Min Act: -0.1700
Data Index: 6937347 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1243. Min Range: -4.1243
Max Act: 4.0617. Min Act: -0.1700
Data Index: 6224538 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9992. Min Act: -0.1700
Data Index: 8226447 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9680. Min Act: -0.1700
Data Index: 337658 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9680. Min Act: -0.1700
Data Index: 4085245 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9054. Min Act: -0.1700
Data Index: 7585961 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9054. Min Act: -0.1700
Data Index: 540131 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9054. Min Act: -0.1700
Data Index: 8205997 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9054. Min Act: -0.1700
Data Index: 1427475 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9054. Min Act: -0.1700
Data Index: 6392655 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.9054. Min Act: -0.1700
Data Index: 2698454 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8742. Min Act: -0.1700
Data Index: 4154589 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8742. Min Act: -0.1700
Data Index: 5920632 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8742. Min Act: -0.1700
Data Index: 1427407 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8742. Min Act: -0.1700
Data Index: 3346813 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8742. Min Act: -0.1700
Data Index: 4603284 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8742. Min Act: -0.1700
Data Index: 1559617 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8429. Min Act: -0.1700
Data Index: 8570854 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1243. Min Range: -4.1243
Max Act: 3.8742. Min Act: -0.1700
Data Index: 1951008 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19