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

Dataset: Open Web Text

Neuron 2151 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: 3.5214. Min Range: -3.5214

Max Act: 3.5214. Min Act: -0.1700

Data Index: 5516265 (Open Web Text)

Max Activating Token Index: 94

Text #1

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4798. Min Act: -0.1700

Data Index: 6757431 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4435. Min Act: -0.1700

Data Index: 23213 (Open Web Text)

Max Activating Token Index: 1018

Text #3

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4515. Min Act: -0.1700

Data Index: 7724886 (Open Web Text)

Max Activating Token Index: 120

Text #4

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4510. Min Act: -0.1700

Data Index: 1297061 (Open Web Text)

Max Activating Token Index: 140

Text #5

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4335. Min Act: -0.1700

Data Index: 2847282 (Open Web Text)

Max Activating Token Index: 35

Text #6

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4223. Min Act: -0.1700

Data Index: 3552980 (Open Web Text)

Max Activating Token Index: 47

Text #7

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4241. Min Act: -0.1700

Data Index: 6978234 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4227. Min Act: -0.1700

Data Index: 4620544 (Open Web Text)

Max Activating Token Index: 446

Text #9

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4290. Min Act: -0.1700

Data Index: 4744693 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4179. Min Act: -0.1700

Data Index: 2426151 (Open Web Text)

Max Activating Token Index: 152

Text #11

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4265. Min Act: -0.1700

Data Index: 5164225 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.3907. Min Act: -0.1700

Data Index: 98873 (Open Web Text)

Max Activating Token Index: 142

Text #13

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4059. Min Act: -0.1700

Data Index: 2777864 (Open Web Text)

Max Activating Token Index: 907

Text #14

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.3961. Min Act: -0.1700

Data Index: 7660294 (Open Web Text)

Max Activating Token Index: 264

Text #15

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.4041. Min Act: -0.1700

Data Index: 3172610 (Open Web Text)

Max Activating Token Index: 66

Text #16

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.3857. Min Act: -0.1700

Data Index: 2428701 (Open Web Text)

Max Activating Token Index: 70

Text #17

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.3951. Min Act: -0.1700

Data Index: 886212 (Open Web Text)

Max Activating Token Index: 948

Text #18

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.3911. Min Act: -0.1700

Data Index: 2306612 (Open Web Text)

Max Activating Token Index: 43

Text #19

Max Range: 3.5214. Min Range: -3.5214

Max Act: 3.3952. Min Act: -0.1700

Data Index: 1988976 (Open Web Text)

Max Activating Token Index: 527