Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2596 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.4318. Min Act: -0.0001
Data Index: 330179 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3780. Min Act: -0.0001
Data Index: 39385 (C4 (Web Text))
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3964. Min Act: -0.0001
Data Index: 164712 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3559. Min Act: -0.0001
Data Index: 1150120 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.2977. Min Act: -0.0001
Data Index: 44823 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3366. Min Act: -0.0001
Data Index: 1622863 (Python Code)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3304. Min Act: -0.0001
Data Index: 501086 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3842. Min Act: -0.0001
Data Index: 1050332 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3447. Min Act: -0.0001
Data Index: 8262 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3142. Min Act: -0.0001
Data Index: 771953 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3470. Min Act: -0.0001
Data Index: 503741 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3336. Min Act: -0.0001
Data Index: 518194 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3518. Min Act: -0.0001
Data Index: 1018485 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3455. Min Act: -0.0001
Data Index: 1161749 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3409. Min Act: -0.0001
Data Index: 1078867 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3154. Min Act: -0.0001
Data Index: 19118 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3146. Min Act: -0.0001
Data Index: 489765 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3519. Min Act: -0.0001
Data Index: 1317703 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3278. Min Act: -0.0001
Data Index: 1441369 (Python Code)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4318. Min Range: -0.4318
Max Act: 0.3378. Min Act: -0.0001
Data Index: 1307177 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19