Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2880 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3711. Min Act: -0.1682

Data Index: 1642460 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3535. Min Act: -0.1682

Data Index: 1642458 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3477. Min Act: -0.1682

Data Index: 1042895 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3384. Min Act: -0.1682

Data Index: 8369354 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3350. Min Act: -0.1682

Data Index: 696856 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3365. Min Act: -0.1682

Data Index: 1436586 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3314. Min Act: -0.1682

Data Index: 1169651 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3271. Min Act: -0.1682

Data Index: 5914895 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3250. Min Act: -0.1682

Data Index: 2654481 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3235. Min Act: -0.1682

Data Index: 4044413 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3191. Min Act: -0.1682

Data Index: 1657690 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3125. Min Act: -0.1682

Data Index: 5815473 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3210. Min Act: -0.1682

Data Index: 1787409 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3011. Min Act: -0.1682

Data Index: 2270047 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3085. Min Act: -0.1682

Data Index: 7893254 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3123. Min Act: -0.1682

Data Index: 7090651 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3094. Min Act: -0.1682

Data Index: 5217832 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3105. Min Act: -0.1682

Data Index: 6290588 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3027. Min Act: -0.1682

Data Index: 5123588 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3711. Min Range: -1.3711

Max Act: 1.3103. Min Act: -0.1682

Data Index: 4992832 (Open Web Text)

Max Activating Token Index: 1023