Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2424 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0808. Min Act: -0.0001
Data Index: 1225275 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0795. Min Act: -0.0001
Data Index: 74382 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0665. Min Act: -0.0001
Data Index: 84028 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0701. Min Act: -0.0001
Data Index: 438918 (C4 (Web Text))
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0621. Min Act: -0.0001
Data Index: 862043 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0665. Min Act: -0.0001
Data Index: 412486 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0603. Min Act: -0.0001
Data Index: 286237 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0641. Min Act: -0.0001
Data Index: 296780 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0589. Min Act: -0.0001
Data Index: 207543 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0630. Min Act: -0.0001
Data Index: 214714 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0615. Min Act: -0.0001
Data Index: 603072 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0593. Min Act: -0.0001
Data Index: 535422 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0612. Min Act: -0.0001
Data Index: 671870 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0587. Min Act: -0.0001
Data Index: 665681 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0622. Min Act: -0.0001
Data Index: 696950 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0585. Min Act: -0.0001
Data Index: 1043786 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0624. Min Act: -0.0001
Data Index: 148485 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0601. Min Act: -0.0001
Data Index: 498932 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0580. Min Act: -0.0001
Data Index: 1044212 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0808. Min Range: -0.0808
Max Act: 0.0568. Min Act: -0.0001
Data Index: 1342721 (C4 (Web Text))
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19