Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3912 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.8759. Min Act: -0.0001
Data Index: 1291606 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.6365. Min Act: -0.0001
Data Index: 464736 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.5662. Min Act: -0.0001
Data Index: 988999 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.5440. Min Act: -0.0001
Data Index: 579989 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.4851. Min Act: -0.0001
Data Index: 714705 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.5288. Min Act: -0.0001
Data Index: 304817 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.3191. Min Act: -0.0001
Data Index: 663302 (C4 (Web Text))
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.7049. Min Act: -0.0001
Data Index: 299555 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.2906. Min Act: -0.0001
Data Index: 1020026 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.4333. Min Act: -0.0001
Data Index: 890665 (C4 (Web Text))
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.4078. Min Act: -0.0001
Data Index: 247393 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.4033. Min Act: -0.0001
Data Index: 408324 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.3009. Min Act: -0.0001
Data Index: 90054 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.3429. Min Act: -0.0001
Data Index: 762163 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.3727. Min Act: -0.0001
Data Index: 192003 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.0768. Min Act: -0.0001
Data Index: 950172 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.3839. Min Act: -0.0001
Data Index: 21347 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.1179. Min Act: -0.0001
Data Index: 187316 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.2476. Min Act: -0.0001
Data Index: 531546 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8759. Min Range: -1.8759
Max Act: 1.3549. Min Act: -0.0001
Data Index: 1248845 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19