Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2782 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.7199. Min Act: -0.0001
Data Index: 596648 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.5581. Min Act: -0.0001
Data Index: 587910 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.5031. Min Act: -0.0001
Data Index: 33449 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.5297. Min Act: -0.0001
Data Index: 520110 (C4 (Web Text))
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.3644. Min Act: -0.0001
Data Index: 1230145 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.4097. Min Act: -0.0001
Data Index: 257490 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.3132. Min Act: -0.0001
Data Index: 565604 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.3401. Min Act: -0.0001
Data Index: 1123388 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.3727. Min Act: -0.0001
Data Index: 741942 (C4 (Web Text))
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2888. Min Act: -0.0001
Data Index: 79262 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2898. Min Act: -0.0001
Data Index: 281870 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2806. Min Act: -0.0001
Data Index: 1292670 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2050. Min Act: -0.0001
Data Index: 133900 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2611. Min Act: -0.0001
Data Index: 1199981 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2204. Min Act: -0.0001
Data Index: 702890 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.1701. Min Act: -0.0001
Data Index: 900227 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2020. Min Act: -0.0001
Data Index: 860938 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.1836. Min Act: -0.0001
Data Index: 668826 (C4 (Web Text))
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.1903. Min Act: -0.0001
Data Index: 1276026 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7199. Min Range: -1.7199
Max Act: 1.2631. Min Act: -0.0001
Data Index: 770501 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19