Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6100 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.6222. Min Act: -0.0001
Data Index: 792860 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.7365. Min Act: -0.0001
Data Index: 1239241 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.4901. Min Act: -0.0001
Data Index: 1016078 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.5555. Min Act: -0.0001
Data Index: 1260300 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.3449. Min Act: -0.0001
Data Index: 158847 (C4 (Web Text))
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.5545. Min Act: -0.0001
Data Index: 439440 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.3578. Min Act: -0.0000
Data Index: 1549437 (Python Code)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.2391. Min Act: -0.0001
Data Index: 187051 (C4 (Web Text))
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.2507. Min Act: -0.0001
Data Index: 1242280 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.1352. Min Act: -0.0000
Data Index: 1403033 (Python Code)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.1988. Min Act: -0.0000
Data Index: 1517480 (Python Code)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.4713. Min Act: -0.0001
Data Index: 1423657 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.2287. Min Act: -0.0001
Data Index: 1602672 (Python Code)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.3370. Min Act: -0.0001
Data Index: 1378518 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.3510. Min Act: -0.0000
Data Index: 1656068 (Python Code)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.3106. Min Act: -0.0000
Data Index: 1556081 (Python Code)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.2931. Min Act: -0.0001
Data Index: 317068 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.3014. Min Act: -0.0001
Data Index: 1213078 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.2060. Min Act: -0.0001
Data Index: 1576414 (Python Code)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7365. Min Range: -2.7365
Max Act: 2.1920. Min Act: -0.0000
Data Index: 1555128 (Python Code)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19