Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4099 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.4906. Min Act: -0.0001
Data Index: 496469 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.6035. Min Act: -0.0001
Data Index: 804174 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.5026. Min Act: -0.0001
Data Index: 136435 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.3821. Min Act: -0.0001
Data Index: 1254687 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.1629. Min Act: -0.0001
Data Index: 755637 (C4 (Web Text))
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.2495. Min Act: -0.0001
Data Index: 1008946 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.0596. Min Act: -0.0001
Data Index: 1310721 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6035. Min Range: -2.6035
Max Act: 1.9867. Min Act: -0.0001
Data Index: 1007231 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.1671. Min Act: -0.0001
Data Index: 1153977 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.0137. Min Act: -0.0001
Data Index: 283784 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.0837. Min Act: -0.0001
Data Index: 1036121 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.1471. Min Act: -0.0001
Data Index: 193790 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.0503. Min Act: -0.0001
Data Index: 268548 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6035. Min Range: -2.6035
Max Act: 1.9307. Min Act: -0.0001
Data Index: 1271231 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6035. Min Range: -2.6035
Max Act: 1.9800. Min Act: -0.0001
Data Index: 1188740 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6035. Min Range: -2.6035
Max Act: 2.0791. Min Act: -0.0001
Data Index: 636429 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6035. Min Range: -2.6035
Max Act: 1.9543. Min Act: -0.0001
Data Index: 612658 (C4 (Web Text))
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6035. Min Range: -2.6035
Max Act: 1.9760. Min Act: -0.0001
Data Index: 267503 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6035. Min Range: -2.6035
Max Act: 1.8796. Min Act: -0.0001
Data Index: 329065 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6035. Min Range: -2.6035
Max Act: 1.9337. Min Act: -0.0001
Data Index: 1028925 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19