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

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

Neuron 3429 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: 0.7186. Min Range: -0.7186

Max Act: 0.7186. Min Act: -0.0001

Data Index: 902041 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.6420. Min Act: -0.0001

Data Index: 1018522 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5242. Min Act: -0.0000

Data Index: 637878 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4952. Min Act: -0.0000

Data Index: 142185 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5097. Min Act: -0.0000

Data Index: 97422 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1256072 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.5030. Min Act: -0.0000

Data Index: 522224 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4582. Min Act: -0.0000

Data Index: 543842 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4691. Min Act: -0.0001

Data Index: 606245 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4285. Min Act: -0.0000

Data Index: 79943 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4722. Min Act: -0.0000

Data Index: 815235 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4947. Min Act: -0.0000

Data Index: 815295 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1193092 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.3980. Min Act: -0.0000

Data Index: 162534 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4394. Min Act: -0.0001

Data Index: 1493839 (Python Code)

Max Activating Token Index: 403

Text #15

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4285. Min Act: -0.0000

Data Index: 793859 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4291. Min Act: -0.0000

Data Index: 195400 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1059124 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.4340. Min Act: -0.0001

Data Index: 167665 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.7186. Min Range: -0.7186

Max Act: 0.3935. Min Act: -0.0001

Data Index: 1607627 (Python Code)

Max Activating Token Index: 944