Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1465. Min Range: -5.1465
Max Act: 5.1465. Min Act: -0.1700
Data Index: 3243518 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1465. Min Range: -5.1465
Max Act: 5.1153. Min Act: -0.1700
Data Index: 6931622 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1465. Min Range: -5.1465
Max Act: 5.1465. Min Act: -0.1700
Data Index: 778157 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1465. Min Range: -5.1465
Max Act: 5.0528. Min Act: -0.1700
Data Index: 8049152 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1465. Min Range: -5.1465
Max Act: 5.0215. Min Act: -0.1700
Data Index: 5630906 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9903. Min Act: -0.1700
Data Index: 4309021 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9590. Min Act: -0.1700
Data Index: 7297318 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9590. Min Act: -0.1700
Data Index: 831671 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 1636981 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 6323838 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 4002018 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 3570448 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 3049291 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 1569656 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.8965. Min Act: -0.1700
Data Index: 1981292 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 6841106 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9278. Min Act: -0.1700
Data Index: 3476129 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.8965. Min Act: -0.1700
Data Index: 3621985 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.8965. Min Act: -0.1700
Data Index: 579861 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.8965. Min Act: -0.1700
Data Index: 4348035 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19