Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 676 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2877. Min Act: -0.0001
Data Index: 593803 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2846. Min Act: -0.0001
Data Index: 367318 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2664. Min Act: -0.0001
Data Index: 937608 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2419. Min Act: -0.0001
Data Index: 1295982 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2599. Min Act: -0.0001
Data Index: 277332 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2798. Min Act: -0.0001
Data Index: 1290394 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2267. Min Act: -0.0001
Data Index: 184403 (C4 (Web Text))
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2329. Min Act: -0.0001
Data Index: 361028 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2305. Min Act: -0.0001
Data Index: 390495 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2159. Min Act: -0.0001
Data Index: 1027614 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2244. Min Act: -0.0001
Data Index: 248129 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2133. Min Act: -0.0001
Data Index: 1289620 (C4 (Web Text))
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2297. Min Act: -0.0001
Data Index: 103729 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2129. Min Act: -0.0001
Data Index: 1418028 (Python Code)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2157. Min Act: -0.0001
Data Index: 1057047 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2042. Min Act: -0.0001
Data Index: 805471 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2040. Min Act: -0.0001
Data Index: 999353 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2007. Min Act: -0.0001
Data Index: 1143906 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.2058. Min Act: -0.0001
Data Index: 451297 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2877. Min Range: -0.2877
Max Act: 0.1982. Min Act: -0.0001
Data Index: 1504934 (Python Code)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19