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

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

Neuron 4212 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0808. Min Range: -1.0808

Max Act: 1.0518. Min Act: -0.0000

Data Index: 767992 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 1.0808. Min Range: -1.0808

Max Act: 1.0211. Min Act: -0.0000

Data Index: 248270 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.0808. Min Range: -1.0808

Max Act: 1.0808. Min Act: -0.0000

Data Index: 905755 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8271. Min Act: -0.0000

Data Index: 827610 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 1.0808. Min Range: -1.0808

Max Act: 1.0000. Min Act: -0.0000

Data Index: 189947 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1154840 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1311901 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.9027. Min Act: -0.0000

Data Index: 1088134 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8079. Min Act: -0.0000

Data Index: 877667 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8217. Min Act: -0.0000

Data Index: 688950 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8514. Min Act: -0.0000

Data Index: 697413 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1027816 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8518. Min Act: -0.0000

Data Index: 394038 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1089468 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8564. Min Act: -0.0000

Data Index: 55498 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8288. Min Act: -0.0000

Data Index: 821673 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1100585 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.7997. Min Act: -0.0000

Data Index: 862401 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.7646. Min Act: -0.0000

Data Index: 722262 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 1.0808. Min Range: -1.0808

Max Act: 0.7642. Min Act: -0.0000

Data Index: 578906 (C4 (Web Text))

Max Activating Token Index: 401