Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 36 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.8819. Min Act: -0.0004
Data Index: 731521 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.8123. Min Act: -0.0004
Data Index: 822907 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.8269. Min Act: -0.0004
Data Index: 120800 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.8756. Min Act: -0.0004
Data Index: 765784 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7548. Min Act: -0.0004
Data Index: 1305224 (C4 (Web Text))
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.9013. Min Act: -0.0004
Data Index: 94409 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7444. Min Act: -0.0004
Data Index: 90597 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7456. Min Act: -0.0004
Data Index: 872616 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.6413. Min Act: -0.0004
Data Index: 1082348 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7288. Min Act: -0.0004
Data Index: 558527 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7274. Min Act: -0.0004
Data Index: 67084 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7937. Min Act: -0.0004
Data Index: 255492 (C4 (Web Text))
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.6499. Min Act: -0.0004
Data Index: 26468 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.9018. Min Act: -0.0004
Data Index: 1153115 (C4 (Web Text))
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7420. Min Act: -0.0004
Data Index: 1166690 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.6687. Min Act: -0.0004
Data Index: 400886 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7577. Min Act: -0.0004
Data Index: 320342 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.6898. Min Act: -0.0004
Data Index: 649711 (C4 (Web Text))
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7975. Min Act: -0.0004
Data Index: 542299 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9018. Min Range: -0.9018
Max Act: 0.7477. Min Act: -0.0004
Data Index: 308396 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19