Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2694 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.4854. Min Act: -0.0001
Data Index: 1109484 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.3345. Min Act: -0.0001
Data Index: 977457 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.2467. Min Act: -0.0001
Data Index: 590816 (C4 (Web Text))
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.2765. Min Act: -0.0001
Data Index: 1248500 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.1920. Min Act: -0.0001
Data Index: 515705 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.1118. Min Act: -0.0001
Data Index: 381850 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.1364. Min Act: -0.0001
Data Index: 41790 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.1372. Min Act: -0.0001
Data Index: 6705 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.1226. Min Act: -0.0001
Data Index: 1335491 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.0757. Min Act: -0.0001
Data Index: 1268081 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.2120. Min Act: -0.0001
Data Index: 931682 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.2283. Min Act: -0.0001
Data Index: 8956 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.1067. Min Act: -0.0001
Data Index: 898250 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.1421. Min Act: -0.0001
Data Index: 688140 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.0646. Min Act: -0.0001
Data Index: 18109 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.0782. Min Act: -0.0001
Data Index: 571061 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.0666. Min Act: -0.0001
Data Index: 683921 (C4 (Web Text))
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4854. Min Range: -1.4854
Max Act: 0.9639. Min Act: -0.0001
Data Index: 47474 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4854. Min Range: -1.4854
Max Act: 0.9910. Min Act: -0.0001
Data Index: 1197969 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4854. Min Range: -1.4854
Max Act: 1.0514. Min Act: -0.0001
Data Index: 1298862 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19