Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3979 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.4786. Min Act: -0.0001
Data Index: 754314 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.1524. Min Act: -0.0001
Data Index: 295892 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.0647. Min Act: -0.0001
Data Index: 1282604 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.0381. Min Act: -0.0001
Data Index: 619543 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.0257. Min Act: -0.0001
Data Index: 41064 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9583. Min Act: -0.0001
Data Index: 1285268 (C4 (Web Text))
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.0401. Min Act: -0.0001
Data Index: 957828 (C4 (Web Text))
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.0287. Min Act: -0.0001
Data Index: 1099768 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9648. Min Act: -0.0001
Data Index: 813684 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9931. Min Act: -0.0001
Data Index: 152040 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9776. Min Act: -0.0001
Data Index: 133170 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9599. Min Act: -0.0001
Data Index: 1210196 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9389. Min Act: -0.0001
Data Index: 1325802 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.0224. Min Act: -0.0001
Data Index: 354615 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4786. Min Range: -1.4786
Max Act: 1.0115. Min Act: -0.0001
Data Index: 983115 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.8886. Min Act: -0.0001
Data Index: 47480 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9188. Min Act: -0.0001
Data Index: 11205 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.9472. Min Act: -0.0001
Data Index: 175790 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.8916. Min Act: -0.0001
Data Index: 1194019 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4786. Min Range: -1.4786
Max Act: 0.8409. Min Act: -0.0001
Data Index: 1039392 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19