Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4494 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.4035. Min Act: -0.0000

Data Index: 801687 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1047706 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1349024 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1137163 (C4 (Web Text))

Max Activating Token Index: 191

Text #4

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3697. Min Act: -0.0000

Data Index: 61052 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3670. Min Act: -0.0000

Data Index: 753972 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3761. Min Act: -0.0000

Data Index: 248181 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1201512 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3643. Min Act: 0.0000

Data Index: 431467 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3385. Min Act: -0.0000

Data Index: 452868 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3470. Min Act: -0.0000

Data Index: 707278 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3324. Min Act: 0.0000

Data Index: 428396 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1071365 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3312. Min Act: -0.0000

Data Index: 72041 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3362. Min Act: -0.0000

Data Index: 318249 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1255438 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2911. Min Act: -0.0000

Data Index: 218182 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2979. Min Act: -0.0000

Data Index: 1186184 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.3027. Min Act: -0.0000

Data Index: 310028 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.4106. Min Range: -0.4106

Max Act: 0.2983. Min Act: -0.0000

Data Index: 655669 (C4 (Web Text))

Max Activating Token Index: 566