Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 115 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.8301. Min Act: -0.1700
Data Index: 932044 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.7025. Min Act: -0.1700
Data Index: 649441 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6865. Min Act: -0.1700
Data Index: 1090688 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6223. Min Act: -0.1700
Data Index: 829413 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6384. Min Act: -0.1699
Data Index: 1090206 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6223. Min Act: -0.1700
Data Index: 1009513 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6062. Min Act: -0.1700
Data Index: 338656 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6223. Min Act: -0.1700
Data Index: 296730 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6062. Min Act: -0.1700
Data Index: 304423 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5902. Min Act: -0.1700
Data Index: 555102 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5740. Min Act: -0.1700
Data Index: 1331724 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.6062. Min Act: -0.1700
Data Index: 836026 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5902. Min Act: -0.1700
Data Index: 530499 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5740. Min Act: -0.1700
Data Index: 189032 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5740. Min Act: -0.1700
Data Index: 790994 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5740. Min Act: -0.1700
Data Index: 835604 (C4 (Web Text))
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5256. Min Act: -0.1700
Data Index: 627200 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5579. Min Act: -0.1700
Data Index: 935603 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5579. Min Act: -0.1700
Data Index: 162635 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8301. Min Range: -2.8301
Max Act: 2.5579. Min Act: -0.1700
Data Index: 777064 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19