Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4368 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2592. Min Range: -2.2592
Max Act: 2.1626. Min Act: -0.0001
Data Index: 382399 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2592. Min Range: -2.2592
Max Act: 2.2592. Min Act: -0.0001
Data Index: 197612 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2592. Min Range: -2.2592
Max Act: 2.0261. Min Act: -0.0000
Data Index: 307301 (C4 (Web Text))
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.9701. Min Act: -0.0001
Data Index: 23803 (C4 (Web Text))
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.8822. Min Act: -0.0000
Data Index: 662966 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.7643. Min Act: -0.0001
Data Index: 143393 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.7300. Min Act: -0.0001
Data Index: 1055860 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.8032. Min Act: -0.0000
Data Index: 14452 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.6973. Min Act: -0.0000
Data Index: 226792 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.7094. Min Act: -0.0001
Data Index: 395654 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.6970. Min Act: -0.0001
Data Index: 1105337 (C4 (Web Text))
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.8000. Min Act: -0.0001
Data Index: 115222 (C4 (Web Text))
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.7808. Min Act: -0.0001
Data Index: 893567 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.7829. Min Act: -0.0001
Data Index: 5696 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.7507. Min Act: -0.0001
Data Index: 508757 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.8616. Min Act: -0.0001
Data Index: 278989 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.6539. Min Act: -0.0000
Data Index: 863370 (C4 (Web Text))
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.7439. Min Act: -0.0001
Data Index: 570582 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.5697. Min Act: -0.0001
Data Index: 1052206 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2592. Min Range: -2.2592
Max Act: 1.8294. Min Act: -0.0001
Data Index: 1209987 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19