Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2519 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3399. Min Act: -0.0001

Data Index: 413824 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3364. Min Act: -0.0001

Data Index: 114506 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3288. Min Act: -0.0001

Data Index: 538628 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3313. Min Act: -0.0001

Data Index: 715830 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3372. Min Act: -0.0001

Data Index: 392181 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3169. Min Act: -0.0001

Data Index: 156149 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3204. Min Act: -0.0001

Data Index: 340613 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3153. Min Act: -0.0001

Data Index: 849011 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3121. Min Act: -0.0001

Data Index: 1234706 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3037. Min Act: -0.0001

Data Index: 747939 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1185301 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3082. Min Act: -0.0001

Data Index: 1066808 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1193777 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3103. Min Act: -0.0001

Data Index: 577619 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3086. Min Act: -0.0001

Data Index: 175844 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2875. Min Act: -0.0001

Data Index: 1081870 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2973. Min Act: -0.0001

Data Index: 503698 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3084. Min Act: -0.0001

Data Index: 989862 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2966. Min Act: -0.0001

Data Index: 1133340 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2965. Min Act: -0.0001

Data Index: 649819 (C4 (Web Text))

Max Activating Token Index: 1005