Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3836 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.4723. Min Act: -0.0000

Data Index: 413968 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.3280. Min Act: -0.0000

Data Index: 339096 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.2893. Min Act: -0.0000

Data Index: 1620191 (Python Code)

Max Activating Token Index: 910

Text #3

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.0621. Min Act: -0.0000

Data Index: 1261642 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.1081. Min Act: -0.0000

Data Index: 471850 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.1986. Min Act: -0.0000

Data Index: 617342 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.0894. Min Act: -0.0000

Data Index: 1147549 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.0461. Min Act: -0.0000

Data Index: 562599 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.0352. Min Act: -0.0000

Data Index: 1224466 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.0359. Min Act: -0.0000

Data Index: 440411 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 2.4723. Min Range: -2.4723

Max Act: 2.0365. Min Act: -0.0000

Data Index: 339363 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.9174. Min Act: -0.0000

Data Index: 128599 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.8901. Min Act: -0.0000

Data Index: 1251782 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.9159. Min Act: -0.0000

Data Index: 115157 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.8170. Min Act: -0.0000

Data Index: 725497 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1308213 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.8068. Min Act: -0.0000

Data Index: 140495 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.8933. Min Act: -0.0000

Data Index: 739145 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.7565. Min Act: -0.0000

Data Index: 88460 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 2.4723. Min Range: -2.4723

Max Act: 1.6433. Min Act: -0.0000

Data Index: 356956 (C4 (Web Text))

Max Activating Token Index: 964