Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1095 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.1283. Min Act: -0.0001
Data Index: 1499322 (Python Code)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.1017. Min Act: -0.0001
Data Index: 393705 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.1043. Min Act: -0.0001
Data Index: 1278623 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.1011. Min Act: -0.0001
Data Index: 319636 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0969. Min Act: -0.0001
Data Index: 769383 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0994. Min Act: -0.0001
Data Index: 70955 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0912. Min Act: -0.0001
Data Index: 1163790 (C4 (Web Text))
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0946. Min Act: -0.0001
Data Index: 1203251 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0900. Min Act: -0.0001
Data Index: 933298 (C4 (Web Text))
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0843. Min Act: -0.0001
Data Index: 188255 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0839. Min Act: -0.0001
Data Index: 1054098 (C4 (Web Text))
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0902. Min Act: -0.0001
Data Index: 399363 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0888. Min Act: -0.0001
Data Index: 304743 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0881. Min Act: -0.0001
Data Index: 1006192 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0907. Min Act: -0.0001
Data Index: 685218 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0871. Min Act: -0.0001
Data Index: 29775 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0877. Min Act: -0.0001
Data Index: 623699 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0872. Min Act: -0.0001
Data Index: 1646297 (Python Code)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0866. Min Act: -0.0001
Data Index: 341203 (C4 (Web Text))
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1283. Min Range: -0.1283
Max Act: 0.0864. Min Act: -0.0001
Data Index: 395870 (C4 (Web Text))
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19