Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2065 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3290. Min Act: -0.0001

Data Index: 1085731 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2641. Min Act: -0.0001

Data Index: 1017971 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2632. Min Act: -0.0001

Data Index: 849082 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2602. Min Act: -0.0001

Data Index: 202003 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2519. Min Act: -0.0001

Data Index: 253615 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2435. Min Act: -0.0001

Data Index: 537507 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2073. Min Act: -0.0001

Data Index: 1153180 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2465. Min Act: -0.0001

Data Index: 1287643 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2152. Min Act: -0.0001

Data Index: 981638 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2312. Min Act: -0.0001

Data Index: 352530 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2514. Min Act: -0.0001

Data Index: 791791 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2353. Min Act: -0.0001

Data Index: 365937 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2410. Min Act: -0.0001

Data Index: 310671 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2308. Min Act: -0.0001

Data Index: 670274 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2097. Min Act: -0.0001

Data Index: 449673 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2347. Min Act: -0.0001

Data Index: 432301 (C4 (Web Text))

Max Activating Token Index: 326

Text #16

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1292795 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2415. Min Act: -0.0001

Data Index: 335215 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2251. Min Act: -0.0001

Data Index: 546824 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2145. Min Act: -0.0001

Data Index: 744853 (C4 (Web Text))

Max Activating Token Index: 779