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

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

Neuron 809 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: 4.6046. Min Range: -4.6046

Max Act: 4.6046. Min Act: -0.1700

Data Index: 978057 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.5266. Min Act: -0.1700

Data Index: 1586762 (Python Code)

Max Activating Token Index: 596

Text #2

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.4394. Min Act: -0.1700

Data Index: 1371058 (Python Code)

Max Activating Token Index: 732

Text #3

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3630. Min Act: -0.1700

Data Index: 711484 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3251. Min Act: -0.1700

Data Index: 1486193 (Python Code)

Max Activating Token Index: 218

Text #5

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3580. Min Act: -0.1700

Data Index: 1500244 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.3365. Min Act: -0.1700

Data Index: 873911 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2797. Min Act: -0.1700

Data Index: 861562 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2802. Min Act: -0.1700

Data Index: 30104 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2956. Min Act: -0.1700

Data Index: 1287335 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2972. Min Act: -0.1700

Data Index: 252438 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2544. Min Act: -0.1700

Data Index: 152825 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2488. Min Act: -0.1700

Data Index: 1078841 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2002. Min Act: -0.1700

Data Index: 1187968 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2351. Min Act: -0.1700

Data Index: 944369 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2127. Min Act: -0.1700

Data Index: 394488 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2097. Min Act: -0.1700

Data Index: 694599 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2538. Min Act: -0.1700

Data Index: 939658 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.2093. Min Act: -0.1700

Data Index: 5246 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 4.6046. Min Range: -4.6046

Max Act: 4.1909. Min Act: -0.1700

Data Index: 808721 (C4 (Web Text))

Max Activating Token Index: 77