Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3260 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.4887. Min Act: -0.0001
Data Index: 756069 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.4735. Min Act: -0.0001
Data Index: 220194 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.3665. Min Act: -0.0001
Data Index: 42858 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.2217. Min Act: -0.0001
Data Index: 1125762 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.3384. Min Act: -0.0001
Data Index: 776851 (C4 (Web Text))
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.3121. Min Act: -0.0001
Data Index: 464268 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.2426. Min Act: -0.0001
Data Index: 878938 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.1630. Min Act: -0.0001
Data Index: 188751 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.0976. Min Act: -0.0001
Data Index: 1023943 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.1658. Min Act: -0.0001
Data Index: 178366 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.0100. Min Act: -0.0001
Data Index: 549234 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4887. Min Range: -1.4887
Max Act: 1.0576. Min Act: -0.0001
Data Index: 644419 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.9532. Min Act: -0.0001
Data Index: 1029195 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.9419. Min Act: -0.0001
Data Index: 1176374 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.8944. Min Act: -0.0001
Data Index: 564 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.9200. Min Act: -0.0001
Data Index: 93987 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.9806. Min Act: -0.0001
Data Index: 1131802 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.9705. Min Act: -0.0001
Data Index: 492194 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.9933. Min Act: -0.0001
Data Index: 1052271 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4887. Min Range: -1.4887
Max Act: 0.9501. Min Act: -0.0001
Data Index: 1048561 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19