Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3048 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0004. Min Range: -2.0004
Max Act: 2.0004. Min Act: -0.0001
Data Index: 244923 (C4 (Web Text))
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.7944. Min Act: -0.0001
Data Index: 891504 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.7401. Min Act: -0.0001
Data Index: 181882 (C4 (Web Text))
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.6011. Min Act: -0.0000
Data Index: 925528 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.2146. Min Act: -0.0001
Data Index: 336955 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.5050. Min Act: -0.0001
Data Index: 946691 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.2401. Min Act: -0.0001
Data Index: 1306443 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.4399. Min Act: -0.0000
Data Index: 945851 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.2402. Min Act: -0.0001
Data Index: 317803 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.4553. Min Act: -0.0000
Data Index: 169919 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.0164. Min Act: -0.0001
Data Index: 486643 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.2566. Min Act: -0.0001
Data Index: 964947 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.1460. Min Act: -0.0000
Data Index: 490236 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.3126. Min Act: -0.0001
Data Index: 263858 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.1718. Min Act: -0.0001
Data Index: 471517 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.2413. Min Act: -0.0000
Data Index: 1304026 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.2696. Min Act: -0.0001
Data Index: 221088 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.4588. Min Act: -0.0001
Data Index: 890105 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.0676. Min Act: -0.0000
Data Index: 1152725 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0004. Min Range: -2.0004
Max Act: 1.1666. Min Act: -0.0001
Data Index: 69082 (C4 (Web Text))
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19