Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2060 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.2029. Min Act: -0.0001
Data Index: 236553 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1675. Min Act: -0.0001
Data Index: 971299 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1618. Min Act: -0.0001
Data Index: 903196 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1545. Min Act: -0.0001
Data Index: 432212 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1528. Min Act: -0.0001
Data Index: 841853 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1422. Min Act: -0.0001
Data Index: 160426 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1416. Min Act: -0.0001
Data Index: 919748 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1430. Min Act: -0.0001
Data Index: 711307 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1325. Min Act: -0.0001
Data Index: 1230129 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1327. Min Act: -0.0001
Data Index: 1105301 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1239. Min Act: -0.0001
Data Index: 147898 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1267. Min Act: -0.0001
Data Index: 936416 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1338. Min Act: -0.0001
Data Index: 866946 (C4 (Web Text))
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1291. Min Act: -0.0001
Data Index: 690516 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1277. Min Act: -0.0001
Data Index: 162642 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1370. Min Act: -0.0001
Data Index: 772433 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1255. Min Act: -0.0001
Data Index: 791816 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1214. Min Act: -0.0001
Data Index: 908066 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1253. Min Act: -0.0001
Data Index: 669353 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2029. Min Range: -0.2029
Max Act: 0.1201. Min Act: -0.0001
Data Index: 1325417 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19