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

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

Neuron 5332 in Layer 0

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: 0.0953. Min Range: -0.0953

Max Act: 0.0953. Min Act: -0.0001

Data Index: 452991 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0930. Min Act: -0.0001

Data Index: 5135 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0929. Min Act: -0.0001

Data Index: 68617 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0909. Min Act: -0.0001

Data Index: 421442 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1236984 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1271001 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0922. Min Act: -0.0001

Data Index: 1317155 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1174480 (C4 (Web Text))

Max Activating Token Index: 705

Text #8

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0894. Min Act: -0.0001

Data Index: 600251 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0912. Min Act: -0.0001

Data Index: 179379 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0910. Min Act: -0.0001

Data Index: 1334139 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0893. Min Act: -0.0001

Data Index: 652056 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0884. Min Act: -0.0001

Data Index: 534684 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1132612 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0881. Min Act: -0.0001

Data Index: 586741 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0900. Min Act: -0.0001

Data Index: 279824 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0904. Min Act: -0.0001

Data Index: 484037 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0890. Min Act: -0.0001

Data Index: 320573 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0872. Min Act: -0.0001

Data Index: 715385 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.0953. Min Range: -0.0953

Max Act: 0.0871. Min Act: -0.0001

Data Index: 117104 (C4 (Web Text))

Max Activating Token Index: 504