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

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

Neuron 1634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.3947. Min Act: -0.0001

Data Index: 1040061 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0956. Min Act: -0.0001

Data Index: 408912 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0918. Min Act: -0.0001

Data Index: 887605 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0349. Min Act: -0.0001

Data Index: 541819 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0673. Min Act: -0.0001

Data Index: 248429 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.3947. Min Range: -1.3947

Max Act: 0.9631. Min Act: -0.0001

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0855. Min Act: -0.0001

Data Index: 934174 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0612. Min Act: -0.0001

Data Index: 931447 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0693. Min Act: -0.0001

Data Index: 291955 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 1.3947. Min Range: -1.3947

Max Act: 0.9626. Min Act: -0.0001

Data Index: 1076987 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0762. Min Act: -0.0001

Data Index: 1115253 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 1.3947. Min Range: -1.3947

Max Act: 0.9820. Min Act: -0.0001

Data Index: 258858 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0727. Min Act: -0.0001

Data Index: 589956 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0497. Min Act: -0.0001

Data Index: 1342237 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0224. Min Act: -0.0001

Data Index: 485553 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 1.3947. Min Range: -1.3947

Max Act: 0.9550. Min Act: -0.0001

Data Index: 238887 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.3947. Min Range: -1.3947

Max Act: 0.9831. Min Act: -0.0001

Data Index: 1076071 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 1.3947. Min Range: -1.3947

Max Act: 1.0476. Min Act: -0.0001

Data Index: 510596 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.3947. Min Range: -1.3947

Max Act: 0.9715. Min Act: -0.0001

Data Index: 1323065 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 1.3947. Min Range: -1.3947

Max Act: 0.9697. Min Act: -0.0001

Data Index: 705061 (C4 (Web Text))

Max Activating Token Index: 639