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

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

Neuron 3458 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: 3.0956. Min Range: -3.0956

Max Act: 3.0956. Min Act: -0.0000

Data Index: 1001874 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 3.0956. Min Range: -3.0956

Max Act: 3.0280. Min Act: -0.0000

Data Index: 939434 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8177. Min Act: -0.0001

Data Index: 424669 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8174. Min Act: -0.0001

Data Index: 742082 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8180. Min Act: -0.0001

Data Index: 120781 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.8795. Min Act: -0.0001

Data Index: 1194063 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.7369. Min Act: -0.0000

Data Index: 3735 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.7396. Min Act: -0.0000

Data Index: 940821 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.6973. Min Act: -0.0001

Data Index: 117877 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.5585. Min Act: -0.0001

Data Index: 1340504 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.5505. Min Act: -0.0000

Data Index: 1109586 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.6820. Min Act: -0.0001

Data Index: 1349192 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.6816. Min Act: -0.0000

Data Index: 176697 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.6624. Min Act: -0.0001

Data Index: 967848 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.7334. Min Act: -0.0000

Data Index: 219928 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.5887. Min Act: -0.0001

Data Index: 481761 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.5807. Min Act: -0.0000

Data Index: 925074 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.5581. Min Act: -0.0001

Data Index: 1252365 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.5435. Min Act: -0.0000

Data Index: 103817 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 3.0956. Min Range: -3.0956

Max Act: 2.5060. Min Act: -0.0000

Data Index: 89773 (C4 (Web Text))

Max Activating Token Index: 10