Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2302 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.2485. Min Act: 0.0001
Data Index: 1468853 (The Pile)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.3253. Min Act: 0.0000
Data Index: 220709 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9743. Min Act: -0.0001
Data Index: 78158 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.1205. Min Act: -0.0000
Data Index: 1072705 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.0694. Min Act: -0.0000
Data Index: 1464094 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.0561. Min Act: 0.0001
Data Index: 1759120 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.0852. Min Act: -0.0001
Data Index: 930867 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9379. Min Act: 0.0001
Data Index: 561903 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9904. Min Act: 0.0000
Data Index: 709663 (The Pile)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.0251. Min Act: -0.0000
Data Index: 1965919 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3253. Min Range: -1.3253
Max Act: 1.0130. Min Act: 0.0000
Data Index: 1405097 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.8542. Min Act: 0.0001
Data Index: 813661 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9078. Min Act: 0.0002
Data Index: 695112 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9367. Min Act: 0.0001
Data Index: 729928 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.8652. Min Act: -0.0000
Data Index: 1887405 (The Pile)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9246. Min Act: -0.0000
Data Index: 88274 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9076. Min Act: -0.0000
Data Index: 848332 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9150. Min Act: 0.0001
Data Index: 1551164 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9421. Min Act: 0.0000
Data Index: 1354972 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3253. Min Range: -1.3253
Max Act: 0.9649. Min Act: -0.0001
Data Index: 902372 (The Pile)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19