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

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

Neuron 1534 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.5310. Min Act: -0.0000

Data Index: 321269 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.4917. Min Act: -0.0000

Data Index: 448185 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1600242 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1610557 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1036177 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1421089 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1494779 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3406. Min Act: -0.0000

Data Index: 1631298 (Python Code)

Max Activating Token Index: 459

Text #8

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3041. Min Act: -0.0000

Data Index: 901329 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.2983. Min Act: -0.0000

Data Index: 875943 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3466. Min Act: -0.0000

Data Index: 899530 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1636928 (Python Code)

Max Activating Token Index: 643

Text #12

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1596111 (Python Code)

Max Activating Token Index: 468

Text #13

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3198. Min Act: -0.0000

Data Index: 1160823 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.2940. Min Act: -0.0000

Data Index: 382769 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.2896. Min Act: -0.0000

Data Index: 779223 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1064307 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3022. Min Act: -0.0000

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1419437 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 0.5310. Min Range: -0.5310

Max Act: 0.3220. Min Act: -0.0000

Data Index: 1241451 (C4 (Web Text))

Max Activating Token Index: 364