Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 501 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.3430. Min Act: -0.0001
Data Index: 1631320 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.1223. Min Act: -0.0001
Data Index: 177141 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0918. Min Act: -0.0001
Data Index: 610971 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.1227. Min Act: -0.0001
Data Index: 1267419 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9605. Min Act: -0.0002
Data Index: 1038845 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0737. Min Act: -0.0002
Data Index: 1113015 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0235. Min Act: -0.0002
Data Index: 103381 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0475. Min Act: -0.0001
Data Index: 769918 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9875. Min Act: -0.0001
Data Index: 937759 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0482. Min Act: -0.0001
Data Index: 1318008 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0670. Min Act: -0.0002
Data Index: 800233 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0566. Min Act: -0.0001
Data Index: 133544 (C4 (Web Text))
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0082. Min Act: -0.0001
Data Index: 894334 (C4 (Web Text))
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3430. Min Range: -1.3430
Max Act: 1.0369. Min Act: -0.0001
Data Index: 1079116 (C4 (Web Text))
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9876. Min Act: -0.0001
Data Index: 1545953 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9912. Min Act: -0.0001
Data Index: 909011 (C4 (Web Text))
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9699. Min Act: -0.0002
Data Index: 1319849 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9816. Min Act: -0.0001
Data Index: 179954 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9547. Min Act: -0.0002
Data Index: 1112606 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3430. Min Range: -1.3430
Max Act: 0.9839. Min Act: -0.0002
Data Index: 274031 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19