Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3191 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0507. Min Range: -1.0507

Max Act: 1.0507. Min Act: -0.0000

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9264. Min Act: -0.0000

Data Index: 268082 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9631. Min Act: -0.0000

Data Index: 894361 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9763. Min Act: -0.0001

Data Index: 527939 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9403. Min Act: -0.0001

Data Index: 145088 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1075895 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8649. Min Act: -0.0000

Data Index: 427657 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8849. Min Act: -0.0001

Data Index: 548528 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7885. Min Act: -0.0001

Data Index: 127187 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1157053 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8066. Min Act: -0.0000

Data Index: 77656 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7921. Min Act: -0.0000

Data Index: 590990 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1108772 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.6994. Min Act: -0.0001

Data Index: 1127402 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.8952. Min Act: -0.0001

Data Index: 570833 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7218. Min Act: -0.0000

Data Index: 126897 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7698. Min Act: -0.0001

Data Index: 988917 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7170. Min Act: -0.0001

Data Index: 505379 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7570. Min Act: -0.0000

Data Index: 310043 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 1.0507. Min Range: -1.0507

Max Act: 0.7743. Min Act: -0.0000

Data Index: 443141 (C4 (Web Text))

Max Activating Token Index: 1018