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

Dataset: Open Web Text

Neuron 994 in Layer 2

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: 4.5035. Min Range: -4.5035

Max Act: 4.4926. Min Act: -0.1700

Data Index: 5904145 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.5035. Min Act: -0.1700

Data Index: 7393475 (Open Web Text)

Max Activating Token Index: 219

Text #2

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.4317. Min Act: -0.1700

Data Index: 3617420 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.4333. Min Act: -0.1700

Data Index: 5010423 (Open Web Text)

Max Activating Token Index: 271

Text #4

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3597. Min Act: -0.1700

Data Index: 4711286 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3248. Min Act: -0.1700

Data Index: 4171455 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3689. Min Act: -0.1700

Data Index: 8276700 (Open Web Text)

Max Activating Token Index: 93

Text #7

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3461. Min Act: -0.1700

Data Index: 7687686 (Open Web Text)

Max Activating Token Index: 817

Text #8

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3484. Min Act: -0.1700

Data Index: 6266329 (Open Web Text)

Max Activating Token Index: 59

Text #9

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3168. Min Act: -0.1700

Data Index: 7031731 (Open Web Text)

Max Activating Token Index: 252

Text #10

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.2729. Min Act: -0.1700

Data Index: 765278 (Open Web Text)

Max Activating Token Index: 171

Text #11

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3425. Min Act: -0.1700

Data Index: 4060273 (Open Web Text)

Max Activating Token Index: 963

Text #12

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3074. Min Act: -0.1700

Data Index: 7439359 (Open Web Text)

Max Activating Token Index: 222

Text #13

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3354. Min Act: -0.1700

Data Index: 2942030 (Open Web Text)

Max Activating Token Index: 373

Text #14

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3253. Min Act: -0.1700

Data Index: 7879164 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.2994. Min Act: -0.1700

Data Index: 5003875 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3314. Min Act: -0.1700

Data Index: 6746482 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3063. Min Act: -0.1700

Data Index: 6434423 (Open Web Text)

Max Activating Token Index: 225

Text #18

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.2668. Min Act: -0.1700

Data Index: 3540124 (Open Web Text)

Max Activating Token Index: 37

Text #19

Max Range: 4.5035. Min Range: -4.5035

Max Act: 4.3004. Min Act: -0.1700

Data Index: 425804 (Open Web Text)

Max Activating Token Index: 505