Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4069 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0881. Min Range: -2.0881
Max Act: 2.0881. Min Act: -0.0001
Data Index: 200227 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.5827. Min Act: -0.0001
Data Index: 212921 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.7064. Min Act: -0.0000
Data Index: 960188 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.7926. Min Act: -0.0001
Data Index: 320859 (C4 (Web Text))
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.8274. Min Act: -0.0001
Data Index: 432313 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.7995. Min Act: -0.0001
Data Index: 1286641 (C4 (Web Text))
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.6518. Min Act: -0.0001
Data Index: 934307 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.1666. Min Act: -0.0001
Data Index: 288721 (C4 (Web Text))
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.5055. Min Act: -0.0000
Data Index: 354509 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3636. Min Act: -0.0001
Data Index: 591398 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.5710. Min Act: -0.0001
Data Index: 994540 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3475. Min Act: -0.0001
Data Index: 783656 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3361. Min Act: -0.0001
Data Index: 721109 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3614. Min Act: -0.0000
Data Index: 272613 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3962. Min Act: -0.0001
Data Index: 695046 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3486. Min Act: -0.0000
Data Index: 1281237 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.2588. Min Act: -0.0001
Data Index: 932253 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.2826. Min Act: -0.0001
Data Index: 802610 (C4 (Web Text))
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3059. Min Act: -0.0001
Data Index: 68978 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0881. Min Range: -2.0881
Max Act: 1.3794. Min Act: -0.0001
Data Index: 562558 (C4 (Web Text))
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19