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

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

Neuron 5645 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0487. Min Act: -0.0001

Data Index: 520045 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0485. Min Act: -0.0001

Data Index: 962573 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0482. Min Act: -0.0001

Data Index: 1325912 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1254224 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0477. Min Act: -0.0001

Data Index: 105953 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0473. Min Act: -0.0001

Data Index: 420360 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0468. Min Act: -0.0001

Data Index: 225405 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0463. Min Act: -0.0001

Data Index: 694645 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0467. Min Act: -0.0001

Data Index: 787243 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0468. Min Act: -0.0001

Data Index: 712082 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1326125 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0467. Min Act: -0.0001

Data Index: 843548 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1151803 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0465. Min Act: -0.0001

Data Index: 641018 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0457. Min Act: -0.0001

Data Index: 918264 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0459. Min Act: -0.0001

Data Index: 805163 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0462. Min Act: -0.0001

Data Index: 104775 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1342544 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0452. Min Act: -0.0001

Data Index: 456976 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.0487. Min Range: -0.0487

Max Act: 0.0448. Min Act: -0.0001

Data Index: 84097 (C4 (Web Text))

Max Activating Token Index: 864