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

Dataset: Open Web Text

Neuron 2331 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: 0.3704. Min Range: -0.3704

Max Act: 0.3704. Min Act: -0.1700

Data Index: 6426880 (Open Web Text)

Max Activating Token Index: 255

Text #1

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3660. Min Act: -0.1700

Data Index: 7005720 (Open Web Text)

Max Activating Token Index: 253

Text #2

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3509. Min Act: -0.1700

Data Index: 198553 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3530. Min Act: -0.1700

Data Index: 6315171 (Open Web Text)

Max Activating Token Index: 123

Text #4

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3500. Min Act: -0.1700

Data Index: 4195358 (Open Web Text)

Max Activating Token Index: 624

Text #5

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3474. Min Act: -0.1700

Data Index: 3724011 (Open Web Text)

Max Activating Token Index: 164

Text #6

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3537. Min Act: -0.1700

Data Index: 3626990 (Open Web Text)

Max Activating Token Index: 120

Text #7

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3268. Min Act: -0.1700

Data Index: 2654026 (Open Web Text)

Max Activating Token Index: 11

Text #8

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3397. Min Act: -0.1700

Data Index: 4076566 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3424. Min Act: -0.1700

Data Index: 3415392 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3256. Min Act: -0.1700

Data Index: 8166358 (Open Web Text)

Max Activating Token Index: 69

Text #11

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3286. Min Act: -0.1700

Data Index: 8434673 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3222. Min Act: -0.1700

Data Index: 6732105 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3302. Min Act: -0.1700

Data Index: 4354023 (Open Web Text)

Max Activating Token Index: 299

Text #14

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3134. Min Act: -0.1700

Data Index: 1750386 (Open Web Text)

Max Activating Token Index: 54

Text #15

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3213. Min Act: -0.1700

Data Index: 4444864 (Open Web Text)

Max Activating Token Index: 164

Text #16

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3258. Min Act: -0.1700

Data Index: 1768982 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3215. Min Act: -0.1700

Data Index: 7166496 (Open Web Text)

Max Activating Token Index: 62

Text #18

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3221. Min Act: -0.1700

Data Index: 3281931 (Open Web Text)

Max Activating Token Index: 102

Text #19

Max Range: 0.3704. Min Range: -0.3704

Max Act: 0.3148. Min Act: -0.1700

Data Index: 1825044 (Open Web Text)

Max Activating Token Index: 74