Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4786 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.6840. Min Act: -0.0001
Data Index: 682042 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.9505. Min Act: -0.0001
Data Index: 1354809 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.7650. Min Act: -0.0001
Data Index: 247281 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.6730. Min Act: -0.0001
Data Index: 1245548 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.7611. Min Act: -0.0001
Data Index: 16548 (C4 (Web Text))
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.7306. Min Act: -0.0001
Data Index: 175572 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.7570. Min Act: -0.0001
Data Index: 1242423 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.7641. Min Act: -0.0001
Data Index: 1276093 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.3900. Min Act: -0.0001
Data Index: 616376 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.5077. Min Act: -0.0001
Data Index: 1191191 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.3996. Min Act: -0.0001
Data Index: 454147 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.4636. Min Act: -0.0001
Data Index: 1067964 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.3958. Min Act: -0.0001
Data Index: 553669 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.2592. Min Act: -0.0001
Data Index: 1297710 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.2219. Min Act: -0.0001
Data Index: 578332 (C4 (Web Text))
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.4170. Min Act: -0.0001
Data Index: 1214976 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.2826. Min Act: -0.0001
Data Index: 312389 (C4 (Web Text))
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.2647. Min Act: -0.0001
Data Index: 246283 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.2798. Min Act: -0.0001
Data Index: 367110 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9505. Min Range: -1.9505
Max Act: 1.2810. Min Act: -0.0001
Data Index: 356833 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19