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

Dataset: Open Web Text

Neuron 92 in Layer 3

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: 4.7166. Min Range: -4.7166

Max Act: 4.7166. Min Act: -0.1700

Data Index: 4605001 (Open Web Text)

Max Activating Token Index: 818

Text #1

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.6235. Min Act: -0.1700

Data Index: 3715381 (Open Web Text)

Max Activating Token Index: 524

Text #2

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.6238. Min Act: -0.1700

Data Index: 1184924 (Open Web Text)

Max Activating Token Index: 873

Text #3

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.5769. Min Act: -0.1700

Data Index: 31109 (Open Web Text)

Max Activating Token Index: 262

Text #4

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.5482. Min Act: -0.1700

Data Index: 1648459 (Open Web Text)

Max Activating Token Index: 860

Text #5

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.5205. Min Act: -0.1700

Data Index: 8393521 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.5197. Min Act: -0.1700

Data Index: 3253830 (Open Web Text)

Max Activating Token Index: 517

Text #7

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.4123. Min Act: -0.1700

Data Index: 7511615 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.4128. Min Act: -0.1700

Data Index: 3397780 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.4185. Min Act: -0.1700

Data Index: 7634217 (Open Web Text)

Max Activating Token Index: 152

Text #10

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3778. Min Act: -0.1700

Data Index: 8160529 (Open Web Text)

Max Activating Token Index: 520

Text #11

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3792. Min Act: -0.1700

Data Index: 7771407 (Open Web Text)

Max Activating Token Index: 145

Text #12

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3958. Min Act: -0.1700

Data Index: 2160254 (Open Web Text)

Max Activating Token Index: 904

Text #13

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3680. Min Act: -0.1700

Data Index: 3297017 (Open Web Text)

Max Activating Token Index: 207

Text #14

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3660. Min Act: -0.1700

Data Index: 5779750 (Open Web Text)

Max Activating Token Index: 737

Text #15

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3959. Min Act: -0.1700

Data Index: 7821901 (Open Web Text)

Max Activating Token Index: 532

Text #16

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3534. Min Act: -0.1700

Data Index: 8643089 (Open Web Text)

Max Activating Token Index: 611

Text #17

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3237. Min Act: -0.1700

Data Index: 4214834 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3058. Min Act: -0.1700

Data Index: 7690746 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 4.7166. Min Range: -4.7166

Max Act: 4.3206. Min Act: -0.1700

Data Index: 915084 (Open Web Text)

Max Activating Token Index: 298