Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1013 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.7486. Min Act: -0.0001
Data Index: 417632 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.7525. Min Act: -0.0001
Data Index: 1166439 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.6190. Min Act: -0.0001
Data Index: 1586481 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5483. Min Act: -0.0001
Data Index: 150720 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.6622. Min Act: -0.0001
Data Index: 573531 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5297. Min Act: -0.0001
Data Index: 823528 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5746. Min Act: -0.0001
Data Index: 444622 (The Pile)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.6542. Min Act: -0.0001
Data Index: 80617 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5048. Min Act: -0.0001
Data Index: 425614 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5349. Min Act: -0.0001
Data Index: 1844946 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5752. Min Act: -0.0001
Data Index: 380411 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.6343. Min Act: -0.0001
Data Index: 315217 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5963. Min Act: -0.0002
Data Index: 257120 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5438. Min Act: -0.0001
Data Index: 1964165 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5390. Min Act: -0.0001
Data Index: 1926886 (The Pile)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5770. Min Act: -0.0001
Data Index: 1593063 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5333. Min Act: -0.0001
Data Index: 525863 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5545. Min Act: -0.0001
Data Index: 1566747 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.5790. Min Act: -0.0001
Data Index: 1638601 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7525. Min Range: -0.7525
Max Act: 0.4442. Min Act: -0.0001
Data Index: 1444190 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19