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

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

Neuron 3828 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3461. Min Range: -1.3461

Max Act: 1.3461. Min Act: -0.0000

Data Index: 358065 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.3461. Min Range: -1.3461

Max Act: 1.1740. Min Act: -0.0000

Data Index: 229266 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 1.3461. Min Range: -1.3461

Max Act: 1.0379. Min Act: -0.0000

Data Index: 134138 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.9297. Min Act: -0.0000

Data Index: 487759 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.9402. Min Act: -0.0001

Data Index: 415018 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.9047. Min Act: -0.0000

Data Index: 33752 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8135. Min Act: -0.0000

Data Index: 1327624 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8637. Min Act: -0.0000

Data Index: 942512 (C4 (Web Text))

Max Activating Token Index: 986

Text #8

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8858. Min Act: -0.0001

Data Index: 1121144 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8295. Min Act: -0.0000

Data Index: 539704 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8532. Min Act: -0.0000

Data Index: 792763 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1179523 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8487. Min Act: -0.0000

Data Index: 367442 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8466. Min Act: -0.0001

Data Index: 386046 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.7885. Min Act: -0.0000

Data Index: 708467 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8067. Min Act: -0.0001

Data Index: 876016 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.7857. Min Act: -0.0000

Data Index: 211976 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8544. Min Act: -0.0000

Data Index: 171888 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.8305. Min Act: -0.0000

Data Index: 1088756 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 1.3461. Min Range: -1.3461

Max Act: 0.7994. Min Act: -0.0001

Data Index: 527776 (C4 (Web Text))

Max Activating Token Index: 962