Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2901 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.1559. Min Range: -1.1559
Max Act: 1.1559. Min Act: -0.0001
Data Index: 943456 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.8730. Min Act: -0.0001
Data Index: 589245 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.9850. Min Act: -0.0001
Data Index: 96672 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7953. Min Act: -0.0001
Data Index: 830340 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.8416. Min Act: -0.0001
Data Index: 1105602 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.8213. Min Act: -0.0001
Data Index: 659463 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7779. Min Act: -0.0001
Data Index: 859799 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7933. Min Act: -0.0001
Data Index: 1273886 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.8467. Min Act: -0.0001
Data Index: 970427 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.8052. Min Act: -0.0001
Data Index: 189606 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7444. Min Act: -0.0001
Data Index: 428128 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7434. Min Act: -0.0001
Data Index: 749369 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.6474. Min Act: -0.0001
Data Index: 417710 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7647. Min Act: -0.0001
Data Index: 982410 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7031. Min Act: -0.0001
Data Index: 1103289 (C4 (Web Text))
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7319. Min Act: -0.0001
Data Index: 227663 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7132. Min Act: -0.0001
Data Index: 30475 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7060. Min Act: -0.0001
Data Index: 1107357 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7919. Min Act: -0.0001
Data Index: 931794 (C4 (Web Text))
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1559. Min Range: -1.1559
Max Act: 0.7420. Min Act: -0.0001
Data Index: 239565 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19