Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3932 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.6103. Min Act: -0.0001
Data Index: 1364393 (Python Code)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.5242. Min Act: -0.0001
Data Index: 224124 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.5124. Min Act: -0.0001
Data Index: 266364 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.5278. Min Act: -0.0001
Data Index: 214730 (C4 (Web Text))
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4920. Min Act: -0.0001
Data Index: 276124 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.5033. Min Act: -0.0001
Data Index: 1554255 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4977. Min Act: -0.0001
Data Index: 1626346 (Python Code)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.5505. Min Act: -0.0001
Data Index: 434121 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4932. Min Act: -0.0001
Data Index: 1616872 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4971. Min Act: -0.0001
Data Index: 1623159 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4748. Min Act: -0.0001
Data Index: 1477238 (Python Code)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4610. Min Act: -0.0001
Data Index: 319165 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.5050. Min Act: -0.0001
Data Index: 1647954 (Python Code)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4755. Min Act: -0.0001
Data Index: 929712 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4941. Min Act: -0.0001
Data Index: 590791 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4652. Min Act: -0.0001
Data Index: 283365 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4820. Min Act: -0.0001
Data Index: 1445804 (Python Code)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4496. Min Act: -0.0001
Data Index: 843056 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.5002. Min Act: -0.0001
Data Index: 949148 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6103. Min Range: -0.6103
Max Act: 0.4730. Min Act: -0.0001
Data Index: 1454606 (Python Code)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19