Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2302. Min Act: -0.0001
Data Index: 138432 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2041. Min Act: -0.0001
Data Index: 646488 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2158. Min Act: -0.0001
Data Index: 860679 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2025. Min Act: -0.0001
Data Index: 487181 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1932. Min Act: -0.0001
Data Index: 373260 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2007. Min Act: -0.0001
Data Index: 960257 (C4 (Web Text))
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2007. Min Act: -0.0001
Data Index: 990465 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1906. Min Act: -0.0001
Data Index: 297655 (C4 (Web Text))
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1996. Min Act: -0.0001
Data Index: 295980 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1968. Min Act: -0.0001
Data Index: 1305775 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2004. Min Act: -0.0001
Data Index: 61296 (C4 (Web Text))
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1977. Min Act: -0.0001
Data Index: 857544 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1863. Min Act: -0.0001
Data Index: 1144211 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1952. Min Act: -0.0001
Data Index: 418681 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1877. Min Act: -0.0001
Data Index: 1232512 (C4 (Web Text))
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1973. Min Act: -0.0001
Data Index: 557104 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1707. Min Act: -0.0001
Data Index: 638659 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1988. Min Act: -0.0001
Data Index: 498268 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.2036. Min Act: -0.0001
Data Index: 8241 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2302. Min Range: -0.2302
Max Act: 0.1969. Min Act: -0.0001
Data Index: 306091 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19