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

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

Neuron 1821 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1956. Min Range: -3.1956

Max Act: 3.1956. Min Act: -0.0000

Data Index: 1171554 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.9373. Min Act: 0.0000

Data Index: 403247 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.7378. Min Act: -0.0000

Data Index: 703726 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.6821. Min Act: -0.0000

Data Index: 290210 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.6116. Min Act: -0.0000

Data Index: 115695 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.5952. Min Act: -0.0000

Data Index: 126338 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4541. Min Act: -0.0000

Data Index: 996291 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4994. Min Act: -0.0000

Data Index: 497506 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.3910. Min Act: -0.0000

Data Index: 677118 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4559. Min Act: -0.0000

Data Index: 1132063 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4646. Min Act: -0.0000

Data Index: 787996 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4262. Min Act: -0.0000

Data Index: 1172596 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4183. Min Act: -0.0000

Data Index: 1208039 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4084. Min Act: -0.0000

Data Index: 857447 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.4056. Min Act: -0.0000

Data Index: 830207 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.2690. Min Act: -0.0000

Data Index: 55944 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.2657. Min Act: -0.0000

Data Index: 410629 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.5116. Min Act: -0.0000

Data Index: 1656414 (Python Code)

Max Activating Token Index: 277

Text #18

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.2620. Min Act: -0.0000

Data Index: 1254540 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 3.1956. Min Range: -3.1956

Max Act: 2.3563. Min Act: -0.0000

Data Index: 887476 (C4 (Web Text))

Max Activating Token Index: 750