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

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

Neuron 768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4965. Min Act: -0.0001

Data Index: 325001 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4823. Min Act: -0.0000

Data Index: 319809 (C4 (Web Text))

Max Activating Token Index: 812

Text #2

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4761. Min Act: -0.0000

Data Index: 891038 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.4070. Min Act: -0.0000

Data Index: 754780 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3500. Min Act: -0.0000

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 786

Text #5

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.1967. Min Act: -0.0001

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3314. Min Act: -0.0001

Data Index: 1008152 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3045. Min Act: -0.0000

Data Index: 251415 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1281370 (C4 (Web Text))

Max Activating Token Index: 536

Text #9

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3050. Min Act: -0.0000

Data Index: 893745 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.3021. Min Act: -0.0000

Data Index: 521347 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1229411 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2667. Min Act: -0.0001

Data Index: 320379 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2952. Min Act: -0.0000

Data Index: 808499 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2725. Min Act: -0.0000

Data Index: 952541 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2620. Min Act: -0.0001

Data Index: 460343 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2634. Min Act: -0.0000

Data Index: 668709 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2828. Min Act: -0.0000

Data Index: 344915 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2817. Min Act: -0.0001

Data Index: 25486 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.4965. Min Range: -0.4965

Max Act: 0.2381. Min Act: -0.0001

Data Index: 162113 (C4 (Web Text))

Max Activating Token Index: 599