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

Dataset: Open Web Text

Neuron 3014 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: 1.8055. Min Range: -1.8055

Max Act: 1.8055. Min Act: -0.1501

Data Index: 8672080 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6502. Min Act: -0.1501

Data Index: 1857811 (Open Web Text)

Max Activating Token Index: 994

Text #2

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6587. Min Act: -0.1501

Data Index: 3383872 (Open Web Text)

Max Activating Token Index: 1007

Text #3

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6416. Min Act: -0.1501

Data Index: 2954264 (Open Web Text)

Max Activating Token Index: 322

Text #4

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6313. Min Act: -0.1501

Data Index: 3333577 (Open Web Text)

Max Activating Token Index: 964

Text #5

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6023. Min Act: -0.1501

Data Index: 5778120 (Open Web Text)

Max Activating Token Index: 1005

Text #6

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6196. Min Act: -0.1501

Data Index: 1204902 (Open Web Text)

Max Activating Token Index: 222

Text #7

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6249. Min Act: -0.1501

Data Index: 5778122 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6223. Min Act: -0.1501

Data Index: 2370287 (Open Web Text)

Max Activating Token Index: 649

Text #9

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6207. Min Act: -0.1501

Data Index: 3580001 (Open Web Text)

Max Activating Token Index: 1011

Text #10

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6185. Min Act: -0.1501

Data Index: 5778121 (Open Web Text)

Max Activating Token Index: 1006

Text #11

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6183. Min Act: -0.1501

Data Index: 2370301 (Open Web Text)

Max Activating Token Index: 873

Text #12

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6128. Min Act: -0.1501

Data Index: 1081070 (Open Web Text)

Max Activating Token Index: 420

Text #13

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6079. Min Act: -0.1501

Data Index: 1081072 (Open Web Text)

Max Activating Token Index: 531

Text #14

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6057. Min Act: -0.1501

Data Index: 6488201 (Open Web Text)

Max Activating Token Index: 992

Text #15

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6056. Min Act: -0.1501

Data Index: 6846126 (Open Web Text)

Max Activating Token Index: 998

Text #16

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.6133. Min Act: -0.1501

Data Index: 549356 (Open Web Text)

Max Activating Token Index: 329

Text #17

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.5957. Min Act: -0.1501

Data Index: 4339266 (Open Web Text)

Max Activating Token Index: 1006

Text #18

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.5986. Min Act: -0.1501

Data Index: 2333838 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 1.8055. Min Range: -1.8055

Max Act: 1.5995. Min Act: -0.1501

Data Index: 1849773 (Open Web Text)

Max Activating Token Index: 988