Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1316 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9906. Min Act: -0.1700

Data Index: 386122 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9553. Min Act: -0.1700

Data Index: 237761 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9362. Min Act: -0.1700

Data Index: 21770 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9144. Min Act: -0.1700

Data Index: 1155694 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9341. Min Act: -0.1700

Data Index: 351051 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9133. Min Act: -0.1700

Data Index: 408836 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9024. Min Act: -0.1700

Data Index: 387219 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.9174. Min Act: -0.1700

Data Index: 173142 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8885. Min Act: -0.1700

Data Index: 350083 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8802. Min Act: -0.1700

Data Index: 164685 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8842. Min Act: -0.1700

Data Index: 764836 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8587. Min Act: -0.1700

Data Index: 720120 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8706. Min Act: -0.1700

Data Index: 348980 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8556. Min Act: -0.1700

Data Index: 1172951 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8689. Min Act: -0.1700

Data Index: 567321 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8662. Min Act: -0.1700

Data Index: 772380 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8622. Min Act: -0.1700

Data Index: 853757 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8596. Min Act: -0.1700

Data Index: 899568 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8531. Min Act: -0.1700

Data Index: 205997 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 2.9906. Min Range: -2.9906

Max Act: 2.8486. Min Act: -0.1700

Data Index: 358256 (C4 (Web Text))

Max Activating Token Index: 750