Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2675 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.6241. Min Act: -0.0001
Data Index: 655112 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.6258. Min Act: -0.0001
Data Index: 339795 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.5657. Min Act: -0.0001
Data Index: 490961 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4723. Min Act: -0.0001
Data Index: 511583 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.5151. Min Act: -0.0001
Data Index: 762821 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.5177. Min Act: -0.0001
Data Index: 936516 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4930. Min Act: -0.0001
Data Index: 224057 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.5119. Min Act: -0.0001
Data Index: 758859 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.5400. Min Act: -0.0001
Data Index: 1313021 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4968. Min Act: -0.0001
Data Index: 454997 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4731. Min Act: -0.0001
Data Index: 349237 (C4 (Web Text))
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4549. Min Act: -0.0001
Data Index: 1285726 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4960. Min Act: -0.0001
Data Index: 233085 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4337. Min Act: -0.0001
Data Index: 5755 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4729. Min Act: -0.0001
Data Index: 385790 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4411. Min Act: -0.0001
Data Index: 51050 (C4 (Web Text))
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4464. Min Act: -0.0001
Data Index: 849271 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4540. Min Act: -0.0001
Data Index: 509643 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4189. Min Act: -0.0001
Data Index: 583086 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6258. Min Range: -0.6258
Max Act: 0.4406. Min Act: -0.0001
Data Index: 64511 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19