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

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

Neuron 34 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: 0.3859. Min Range: -0.3859

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1126929 (C4 (Web Text))

Max Activating Token Index: 491

Text #1

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3290. Min Act: -0.0001

Data Index: 617705 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3150. Min Act: -0.0001

Data Index: 336510 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2866. Min Act: -0.0001

Data Index: 498945 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3154. Min Act: -0.0000

Data Index: 978978 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2970. Min Act: -0.0001

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2962. Min Act: -0.0001

Data Index: 801346 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2841. Min Act: -0.0001

Data Index: 955627 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3005. Min Act: -0.0001

Data Index: 80820 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2890. Min Act: -0.0001

Data Index: 574728 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2687. Min Act: -0.0001

Data Index: 28121 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2864. Min Act: -0.0001

Data Index: 548365 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2844. Min Act: -0.0001

Data Index: 85206 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2841. Min Act: -0.0001

Data Index: 161164 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3029. Min Act: -0.0001

Data Index: 90976 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2620. Min Act: -0.0001

Data Index: 527705 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2728. Min Act: -0.0001

Data Index: 1228399 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2725. Min Act: -0.0001

Data Index: 594515 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2906. Min Act: -0.0001

Data Index: 232992 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2787. Min Act: -0.0001

Data Index: 207867 (C4 (Web Text))

Max Activating Token Index: 683