Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6063 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.3037. Min Range: -1.3037
Max Act: 1.3037. Min Act: -0.0001
Data Index: 753996 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3037. Min Range: -1.3037
Max Act: 1.2791. Min Act: -0.0001
Data Index: 529196 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3037. Min Range: -1.3037
Max Act: 1.1485. Min Act: -0.0001
Data Index: 882121 (C4 (Web Text))
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3037. Min Range: -1.3037
Max Act: 1.1655. Min Act: -0.0001
Data Index: 820511 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.9649. Min Act: -0.0001
Data Index: 1277654 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.9657. Min Act: -0.0001
Data Index: 1009995 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.9700. Min Act: -0.0001
Data Index: 1655002 (Python Code)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.7882. Min Act: -0.0001
Data Index: 1225982 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.7855. Min Act: -0.0001
Data Index: 391564 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.7550. Min Act: -0.0001
Data Index: 794501 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.7039. Min Act: -0.0001
Data Index: 909338 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.7091. Min Act: -0.0001
Data Index: 504757 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.6948. Min Act: -0.0001
Data Index: 1348403 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.7071. Min Act: -0.0001
Data Index: 959987 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.5867. Min Act: -0.0001
Data Index: 1092111 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.6416. Min Act: -0.0001
Data Index: 1392477 (Python Code)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.6494. Min Act: -0.0001
Data Index: 584228 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.6369. Min Act: -0.0001
Data Index: 232209 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.6290. Min Act: -0.0001
Data Index: 1235604 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3037. Min Range: -1.3037
Max Act: 0.6821. Min Act: -0.0001
Data Index: 1173124 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19