Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2796 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4920. Min Act: -0.0000

Data Index: 757248 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1123921 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3956. Min Act: -0.0001

Data Index: 444051 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1555416 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3843. Min Act: -0.0000

Data Index: 47042 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3930. Min Act: -0.0000

Data Index: 436460 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3747. Min Act: -0.0000

Data Index: 39154 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3521. Min Act: -0.0000

Data Index: 59222 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3743. Min Act: -0.0000

Data Index: 782801 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1311134 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3763. Min Act: -0.0000

Data Index: 160053 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1309515 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3514. Min Act: -0.0000

Data Index: 370428 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1296193 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1193318 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3341. Min Act: -0.0001

Data Index: 348902 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3318. Min Act: -0.0000

Data Index: 697536 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3189. Min Act: -0.0000

Data Index: 801717 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1011057 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.4920. Min Range: -0.4920

Max Act: 0.3443. Min Act: -0.0000

Data Index: 385380 (C4 (Web Text))

Max Activating Token Index: 579