Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 216 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4861. Min Range: -2.4861

Max Act: 2.3066. Min Act: -0.0000

Data Index: 31187 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 2.4861. Min Range: -2.4861

Max Act: 2.4861. Min Act: -0.0000

Data Index: 265852 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.8216. Min Act: -0.0000

Data Index: 342907 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.6295. Min Act: -0.0000

Data Index: 851577 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.6241. Min Act: -0.0000

Data Index: 988683 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1066398 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.5714. Min Act: -0.0000

Data Index: 310466 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.5120. Min Act: -0.0000

Data Index: 169450 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.4822. Min Act: -0.0000

Data Index: 660351 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.3918. Min Act: -0.0000

Data Index: 161319 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.4483. Min Act: -0.0000

Data Index: 904103 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.3783. Min Act: -0.0000

Data Index: 26903 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.2961. Min Act: -0.0000

Data Index: 826208 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.3791. Min Act: -0.0000

Data Index: 1062244 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.3314. Min Act: -0.0000

Data Index: 1010419 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.2458. Min Act: -0.0000

Data Index: 591772 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.2407. Min Act: -0.0000

Data Index: 440127 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.2399. Min Act: -0.0000

Data Index: 205485 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1063719 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 2.4861. Min Range: -2.4861

Max Act: 1.3644. Min Act: -0.0000

Data Index: 73407 (C4 (Web Text))

Max Activating Token Index: 106