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

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

Neuron 2191 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2952. Min Act: -0.0001

Data Index: 1201363 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2534. Min Act: -0.0001

Data Index: 240959 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2602. Min Act: -0.0001

Data Index: 1161106 (C4 (Web Text))

Max Activating Token Index: 87

Text #3

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2565. Min Act: -0.0001

Data Index: 842548 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2453. Min Act: -0.0001

Data Index: 680430 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2622. Min Act: -0.0001

Data Index: 984966 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2600. Min Act: -0.0001

Data Index: 741471 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2405. Min Act: -0.0001

Data Index: 3123 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2488. Min Act: -0.0001

Data Index: 1119541 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2313. Min Act: -0.0001

Data Index: 830025 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2387. Min Act: -0.0001

Data Index: 222114 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1015769 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2428. Min Act: -0.0001

Data Index: 312032 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1237948 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2399. Min Act: -0.0001

Data Index: 506256 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2487. Min Act: -0.0001

Data Index: 311951 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2373. Min Act: -0.0001

Data Index: 1047531 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2186. Min Act: -0.0001

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2172. Min Act: -0.0001

Data Index: 607928 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.2952. Min Range: -0.2952

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1044943 (C4 (Web Text))

Max Activating Token Index: 263