Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1375 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3350. Min Act: -0.0002

Data Index: 988517 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3337. Min Act: -0.0002

Data Index: 601978 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3207. Min Act: -0.0002

Data Index: 1250952 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3209. Min Act: -0.0002

Data Index: 383234 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3185. Min Act: -0.0002

Data Index: 120881 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3117. Min Act: -0.0002

Data Index: 378621 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3083. Min Act: -0.0002

Data Index: 48215 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3143. Min Act: -0.0002

Data Index: 200081 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3070. Min Act: -0.0002

Data Index: 1084648 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2899. Min Act: -0.0002

Data Index: 114341 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2979. Min Act: -0.0002

Data Index: 20315 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2971. Min Act: -0.0002

Data Index: 531548 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2999. Min Act: -0.0002

Data Index: 1318155 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2957. Min Act: -0.0002

Data Index: 569454 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2930. Min Act: -0.0002

Data Index: 18744 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2914. Min Act: -0.0002

Data Index: 174397 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2915. Min Act: -0.0002

Data Index: 565475 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2899. Min Act: -0.0002

Data Index: 752828 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2837. Min Act: -0.0002

Data Index: 339284 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2872. Min Act: -0.0002

Data Index: 214301 (C4 (Web Text))

Max Activating Token Index: 79