Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.7375. Min Act: -0.1700
Data Index: 6847217 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.4250. Min Act: -0.1700
Data Index: 4935238 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.3625. Min Act: -0.1700
Data Index: 5433104 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.3000. Min Act: -0.1700
Data Index: 8696112 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.1750. Min Act: -0.1700
Data Index: 4325867 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.1125. Min Act: -0.1700
Data Index: 5522273 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.0500. Min Act: -0.1700
Data Index: 2501597 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7375. Min Range: -9.7375
Max Act: 9.0500. Min Act: -0.1700
Data Index: 4767365 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.9250. Min Act: -0.1700
Data Index: 7181636 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.9875. Min Act: -0.1700
Data Index: 4162241 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.9875. Min Act: -0.1700
Data Index: 5617950 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.9250. Min Act: -0.1700
Data Index: 6846809 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.9250. Min Act: -0.1700
Data Index: 6049522 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.9250. Min Act: -0.1700
Data Index: 506941 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.9250. Min Act: -0.1700
Data Index: 3451422 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.8625. Min Act: -0.1700
Data Index: 29413 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.8000. Min Act: -0.1700
Data Index: 2228762 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.8625. Min Act: -0.1700
Data Index: 6855029 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.8625. Min Act: -0.1700
Data Index: 6981922 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7375. Min Range: -9.7375
Max Act: 8.8625. Min Act: -0.1700
Data Index: 6999503 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #19