Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 682 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.1374. Min Act: -0.0001
Data Index: 1224265 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0781. Min Act: -0.0001
Data Index: 299368 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0718. Min Act: -0.0001
Data Index: 312140 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0636. Min Act: -0.0001
Data Index: 1461548 (Python Code)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0639. Min Act: -0.0001
Data Index: 1019035 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0601. Min Act: -0.0001
Data Index: 915565 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0591. Min Act: -0.0001
Data Index: 1528006 (Python Code)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0623. Min Act: -0.0000
Data Index: 621720 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0571. Min Act: -0.0001
Data Index: 50084 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0579. Min Act: -0.0001
Data Index: 746173 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0544. Min Act: -0.0001
Data Index: 1499599 (Python Code)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0563. Min Act: -0.0001
Data Index: 896554 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0532. Min Act: -0.0000
Data Index: 1100399 (C4 (Web Text))
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0553. Min Act: -0.0001
Data Index: 897520 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0574. Min Act: -0.0000
Data Index: 351293 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0551. Min Act: -0.0001
Data Index: 208433 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0543. Min Act: -0.0001
Data Index: 751972 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0550. Min Act: -0.0000
Data Index: 907675 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0559. Min Act: -0.0001
Data Index: 1035215 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1374. Min Range: -0.1374
Max Act: 0.0545. Min Act: -0.0001
Data Index: 646129 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19