Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1462 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.1174. Min Act: -0.1700
Data Index: 4885375 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.1332. Min Act: -0.1700
Data Index: 3770976 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.1174. Min Act: -0.1700
Data Index: 8669824 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1332. Min Range: -3.1332
Max Act: 3.0386. Min Act: -0.1700
Data Index: 719720 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9912. Min Act: -0.1700
Data Index: 424759 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9912. Min Act: -0.1700
Data Index: 8669825 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9912. Min Act: -0.1700
Data Index: 5940393 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9595. Min Act: -0.1700
Data Index: 4384549 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9754. Min Act: -0.1700
Data Index: 8768806 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9595. Min Act: -0.1700
Data Index: 7495127 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9279. Min Act: -0.1700
Data Index: 5239905 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9279. Min Act: -0.1700
Data Index: 2595120 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9120. Min Act: -0.1700
Data Index: 4920010 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9120. Min Act: -0.1700
Data Index: 545217 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.8962. Min Act: -0.1700
Data Index: 4528352 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.9120. Min Act: -0.1700
Data Index: 928335 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.8962. Min Act: -0.1700
Data Index: 8669823 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.8486. Min Act: -0.1700
Data Index: 3699419 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.8644. Min Act: -0.1700
Data Index: 6457497 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1332. Min Range: -3.1332
Max Act: 2.8644. Min Act: -0.1700
Data Index: 7268281 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19