Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 54 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.9799. Min Act: -0.0001
Data Index: 1155678 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.8236. Min Act: -0.0001
Data Index: 169773 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.8396. Min Act: -0.0001
Data Index: 1178927 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.7857. Min Act: -0.0001
Data Index: 654619 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.7365. Min Act: -0.0001
Data Index: 728516 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.7276. Min Act: -0.0001
Data Index: 262611 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.7430. Min Act: -0.0001
Data Index: 469503 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.7094. Min Act: -0.0001
Data Index: 659855 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6936. Min Act: -0.0001
Data Index: 998592 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.7861. Min Act: -0.0001
Data Index: 176362 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.7267. Min Act: -0.0001
Data Index: 772746 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6208. Min Act: -0.0001
Data Index: 416329 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.5756. Min Act: -0.0001
Data Index: 484514 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6760. Min Act: -0.0001
Data Index: 1306173 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6596. Min Act: -0.0001
Data Index: 570305 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6833. Min Act: -0.0001
Data Index: 1184694 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6756. Min Act: -0.0001
Data Index: 1096725 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6772. Min Act: -0.0001
Data Index: 1187014 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6705. Min Act: -0.0001
Data Index: 469119 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9799. Min Range: -0.9799
Max Act: 0.6661. Min Act: -0.0001
Data Index: 1058689 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19