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

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

Neuron 3467 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6789. Min Act: -0.0001

Data Index: 555221 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6594. Min Act: -0.0001

Data Index: 1226692 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6964. Min Act: -0.0001

Data Index: 1192467 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1237455 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6110. Min Act: -0.0001

Data Index: 122605 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6197. Min Act: -0.0001

Data Index: 741376 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5752. Min Act: -0.0001

Data Index: 637675 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5951. Min Act: -0.0001

Data Index: 700848 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6349. Min Act: -0.0001

Data Index: 835462 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6070. Min Act: -0.0001

Data Index: 1051508 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5882. Min Act: -0.0001

Data Index: 1061490 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5773. Min Act: -0.0001

Data Index: 775731 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1024874 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6197. Min Act: -0.0001

Data Index: 335498 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5972. Min Act: -0.0001

Data Index: 219609 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6176. Min Act: -0.0001

Data Index: 253754 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.6323. Min Act: -0.0001

Data Index: 271818 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5949. Min Act: -0.0001

Data Index: 985610 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1322782 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.6964. Min Range: -0.6964

Max Act: 0.5851. Min Act: -0.0001

Data Index: 1159240 (C4 (Web Text))

Max Activating Token Index: 264