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

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

Neuron 1235 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.4265. Min Act: -0.0002

Data Index: 1045254 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.4071. Min Act: -0.0002

Data Index: 1281248 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3816. Min Act: -0.0002

Data Index: 1264917 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3534. Min Act: -0.0003

Data Index: 148958 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3443. Min Act: -0.0002

Data Index: 374487 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3489. Min Act: -0.0002

Data Index: 1316544 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3475. Min Act: -0.0002

Data Index: 26223 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3389. Min Act: -0.0002

Data Index: 434952 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3320. Min Act: -0.0002

Data Index: 97913 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3446. Min Act: -0.0002

Data Index: 870706 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3274. Min Act: -0.0002

Data Index: 6044 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3269. Min Act: -0.0002

Data Index: 291239 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3151. Min Act: -0.0002

Data Index: 1003909 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3132. Min Act: -0.0002

Data Index: 944506 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3095. Min Act: -0.0002

Data Index: 1215316 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.2981. Min Act: -0.0002

Data Index: 680421 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3085. Min Act: -0.0002

Data Index: 1166578 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3081. Min Act: -0.0002

Data Index: 1219988 (C4 (Web Text))

Max Activating Token Index: 484

Text #18

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3019. Min Act: -0.0002

Data Index: 830001 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.4265. Min Range: -0.4265

Max Act: 0.3078. Min Act: -0.0003

Data Index: 440805 (C4 (Web Text))

Max Activating Token Index: 707