Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 711 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7768. Min Range: -2.7768
Max Act: 2.7768. Min Act: -0.0001
Data Index: 1175422 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.5063. Min Act: -0.0001
Data Index: 1289632 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.6439. Min Act: -0.0001
Data Index: 350931 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.6058. Min Act: -0.0001
Data Index: 146539 (C4 (Web Text))
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.4167. Min Act: -0.0001
Data Index: 929571 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.5081. Min Act: -0.0001
Data Index: 174211 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3980. Min Act: -0.0001
Data Index: 645242 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.4573. Min Act: -0.0001
Data Index: 142828 (C4 (Web Text))
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.4552. Min Act: -0.0001
Data Index: 311389 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3464. Min Act: -0.0001
Data Index: 505600 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3432. Min Act: -0.0001
Data Index: 803683 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3313. Min Act: -0.0001
Data Index: 42950 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3933. Min Act: -0.0001
Data Index: 24741 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3826. Min Act: -0.0001
Data Index: 956119 (C4 (Web Text))
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3039. Min Act: -0.0001
Data Index: 29059 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3745. Min Act: -0.0001
Data Index: 371609 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3711. Min Act: -0.0001
Data Index: 127876 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3158. Min Act: -0.0001
Data Index: 832015 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.3767. Min Act: -0.0001
Data Index: 214026 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7768. Min Range: -2.7768
Max Act: 1.2892. Min Act: -0.0001
Data Index: 281606 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19