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

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

Neuron 1170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.7942. Min Act: -0.0003

Data Index: 162737 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.7214. Min Act: -0.0003

Data Index: 377187 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.6607. Min Act: -0.0003

Data Index: 1277888 (C4 (Web Text))

Max Activating Token Index: 185

Text #3

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.5099. Min Act: -0.0003

Data Index: 1161177 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.4885. Min Act: -0.0003

Data Index: 1057397 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.3399. Min Act: -0.0003

Data Index: 393797 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.4547. Min Act: -0.0003

Data Index: 409782 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.4876. Min Act: -0.0003

Data Index: 1103278 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.4264. Min Act: -0.0003

Data Index: 19736 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.4093. Min Act: -0.0003

Data Index: 922897 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.4063. Min Act: -0.0003

Data Index: 484085 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.4093. Min Act: -0.0003

Data Index: 634255 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.2806. Min Act: -0.0003

Data Index: 137905 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.3931. Min Act: -0.0003

Data Index: 331523 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.3721. Min Act: -0.0003

Data Index: 1088515 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.3143. Min Act: -0.0003

Data Index: 721659 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.3095. Min Act: -0.0003

Data Index: 135303 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.3877. Min Act: -0.0003

Data Index: 571225 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.2968. Min Act: -0.0003

Data Index: 1021355 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 1.7942. Min Range: -1.7942

Max Act: 1.3850. Min Act: -0.0003

Data Index: 1227949 (C4 (Web Text))

Max Activating Token Index: 240