Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3203 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.4868. Min Act: -0.0001
Data Index: 1609773 (Python Code)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.4843. Min Act: -0.0001
Data Index: 1452834 (Python Code)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.4264. Min Act: -0.0001
Data Index: 1495339 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.4218. Min Act: -0.0001
Data Index: 1429879 (Python Code)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.4225. Min Act: -0.0001
Data Index: 1437485 (Python Code)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.4214. Min Act: -0.0001
Data Index: 1645558 (Python Code)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3937. Min Act: -0.0001
Data Index: 1622587 (Python Code)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3541. Min Act: -0.0001
Data Index: 1591322 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3497. Min Act: -0.0001
Data Index: 1616291 (Python Code)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.4157. Min Act: -0.0001
Data Index: 1367552 (Python Code)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3231. Min Act: -0.0001
Data Index: 1529494 (Python Code)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3196. Min Act: -0.0001
Data Index: 1623336 (Python Code)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3492. Min Act: -0.0001
Data Index: 1586902 (Python Code)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3932. Min Act: -0.0001
Data Index: 1390665 (Python Code)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3427. Min Act: -0.0001
Data Index: 1544821 (Python Code)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3648. Min Act: -0.0001
Data Index: 1624873 (Python Code)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.2816. Min Act: -0.0001
Data Index: 1577686 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.3579. Min Act: -0.0001
Data Index: 1528111 (Python Code)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.2787. Min Act: -0.0001
Data Index: 1403472 (Python Code)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4868. Min Range: -1.4868
Max Act: 1.2718. Min Act: -0.0001
Data Index: 1612421 (Python Code)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19