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

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

Neuron 2754 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8418. Min Act: -0.0001

Data Index: 771924 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.8810. Min Act: -0.0000

Data Index: 146977 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6607. Min Act: -0.0001

Data Index: 1598934 (Python Code)

Max Activating Token Index: 847

Text #3

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6733. Min Act: -0.0001

Data Index: 1200615 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6089. Min Act: -0.0001

Data Index: 1213798 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.6157. Min Act: -0.0000

Data Index: 110868 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5718. Min Act: -0.0001

Data Index: 819143 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5632. Min Act: -0.0000

Data Index: 293058 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5390. Min Act: -0.0001

Data Index: 307612 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5573. Min Act: -0.0000

Data Index: 744204 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5365. Min Act: -0.0001

Data Index: 1377678 (Python Code)

Max Activating Token Index: 1009

Text #11

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5163. Min Act: -0.0001

Data Index: 1379431 (Python Code)

Max Activating Token Index: 875

Text #12

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5454. Min Act: -0.0001

Data Index: 1611788 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5208. Min Act: -0.0001

Data Index: 1159510 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1318553 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5066. Min Act: -0.0001

Data Index: 949018 (C4 (Web Text))

Max Activating Token Index: 258

Text #16

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1124915 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5493. Min Act: -0.0001

Data Index: 834476 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1163515 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.8810. Min Range: -0.8810

Max Act: 0.4949. Min Act: -0.0001

Data Index: 1634359 (Python Code)

Max Activating Token Index: 812