Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 32 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.9176. Min Act: -0.0001

Data Index: 1581393 (Python Code)

Max Activating Token Index: 399

Text #1

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1479482 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.9026. Min Act: -0.0001

Data Index: 1500933 (Python Code)

Max Activating Token Index: 51

Text #3

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1509969 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7968. Min Act: -0.0001

Data Index: 1572089 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8567. Min Act: -0.0001

Data Index: 1415232 (Python Code)

Max Activating Token Index: 406

Text #6

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1636132 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8231. Min Act: -0.0000

Data Index: 1455334 (Python Code)

Max Activating Token Index: 61

Text #8

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8212. Min Act: -0.0001

Data Index: 1592090 (Python Code)

Max Activating Token Index: 234

Text #9

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1416025 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1640526 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.8121. Min Act: -0.0001

Data Index: 1508562 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1621056 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1603610 (Python Code)

Max Activating Token Index: 332

Text #14

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7631. Min Act: -0.0001

Data Index: 1424322 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7407. Min Act: -0.0001

Data Index: 1562873 (Python Code)

Max Activating Token Index: 89

Text #16

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7449. Min Act: -0.0001

Data Index: 1368588 (Python Code)

Max Activating Token Index: 122

Text #17

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6954. Min Act: -0.0001

Data Index: 1562945 (Python Code)

Max Activating Token Index: 259

Text #18

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1459598 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 0.9366. Min Range: -0.9366

Max Act: 0.6734. Min Act: -0.0001

Data Index: 1450575 (Python Code)

Max Activating Token Index: 965