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

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

Neuron 1913 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.4050. Min Act: -0.0001

Data Index: 1508329 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3672. Min Act: -0.0001

Data Index: 1656927 (Python Code)

Max Activating Token Index: 895

Text #2

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3452. Min Act: -0.0001

Data Index: 1605417 (Python Code)

Max Activating Token Index: 842

Text #3

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3538. Min Act: -0.0001

Data Index: 1497545 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1624686 (Python Code)

Max Activating Token Index: 634

Text #5

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3329. Min Act: -0.0001

Data Index: 1569991 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3395. Min Act: -0.0001

Data Index: 1627205 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1476233 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3250. Min Act: -0.0001

Data Index: 804798 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1385232 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1531797 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1631744 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3155. Min Act: -0.0001

Data Index: 1121818 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1362623 (Python Code)

Max Activating Token Index: 513

Text #14

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2983. Min Act: -0.0001

Data Index: 1580212 (Python Code)

Max Activating Token Index: 55

Text #15

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.2970. Min Act: -0.0001

Data Index: 1423820 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3044. Min Act: -0.0001

Data Index: 1476753 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3056. Min Act: -0.0001

Data Index: 1364437 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3111. Min Act: -0.0001

Data Index: 1493253 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 0.4050. Min Range: -0.4050

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1590511 (Python Code)

Max Activating Token Index: 116