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

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

Neuron 1826 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: 2.1347. Min Range: -2.1347

Max Act: 2.1347. Min Act: -0.0000

Data Index: 92593 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 2.1347. Min Range: -2.1347

Max Act: 2.0019. Min Act: -0.0000

Data Index: 1125002 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 2.1347. Min Range: -2.1347

Max Act: 2.0612. Min Act: -0.0000

Data Index: 260574 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9795. Min Act: -0.0000

Data Index: 452082 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 2.1347. Min Range: -2.1347

Max Act: 2.0178. Min Act: -0.0001

Data Index: 277349 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9637. Min Act: -0.0001

Data Index: 672895 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9534. Min Act: -0.0001

Data Index: 1412297 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.8208. Min Act: -0.0001

Data Index: 985671 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.8500. Min Act: -0.0000

Data Index: 349266 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9042. Min Act: -0.0001

Data Index: 1649353 (Python Code)

Max Activating Token Index: 960

Text #10

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.8396. Min Act: -0.0000

Data Index: 1062583 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9342. Min Act: -0.0000

Data Index: 1325452 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.8141. Min Act: -0.0001

Data Index: 1423355 (Python Code)

Max Activating Token Index: 886

Text #13

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.8914. Min Act: -0.0000

Data Index: 1269592 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.8330. Min Act: -0.0001

Data Index: 1206797 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.7738. Min Act: -0.0001

Data Index: 1217806 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9354. Min Act: -0.0001

Data Index: 52905 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.7743. Min Act: -0.0000

Data Index: 85092 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9208. Min Act: -0.0001

Data Index: 708464 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 2.1347. Min Range: -2.1347

Max Act: 1.9034. Min Act: -0.0000

Data Index: 381570 (C4 (Web Text))

Max Activating Token Index: 800