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

Dataset: The Pile

Neuron 2131 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1863945 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.7408. Min Act: -0.0000

Data Index: 529458 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5999. Min Act: -0.0000

Data Index: 1550530 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6597. Min Act: -0.0000

Data Index: 1161280 (The Pile)

Max Activating Token Index: 72

Text #4

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.6415. Min Act: -0.0000

Data Index: 1475868 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5808. Min Act: -0.0000

Data Index: 259222 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1366578 (The Pile)

Max Activating Token Index: 654

Text #7

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1375215 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5593. Min Act: -0.0000

Data Index: 490058 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1444678 (The Pile)

Max Activating Token Index: 590

Text #10

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5461. Min Act: -0.0000

Data Index: 164560 (The Pile)

Max Activating Token Index: 686

Text #11

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5629. Min Act: -0.0000

Data Index: 959957 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5215. Min Act: -0.0000

Data Index: 982090 (The Pile)

Max Activating Token Index: 336

Text #13

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5022. Min Act: -0.0000

Data Index: 440196 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5249. Min Act: -0.0000

Data Index: 540135 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.4686. Min Act: -0.0000

Data Index: 693340 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5093. Min Act: 0.0000

Data Index: 1899785 (The Pile)

Max Activating Token Index: 849

Text #17

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1214943 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1227028 (The Pile)

Max Activating Token Index: 311

Text #19

Max Range: 0.7408. Min Range: -0.7408

Max Act: 0.4755. Min Act: -0.0000

Data Index: 198741 (The Pile)

Max Activating Token Index: 805