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

Dataset: Open Web Text

Neuron 2136 in Layer 1

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: 2.6375. Min Range: -2.6375

Max Act: 2.6375. Min Act: -0.1700

Data Index: 4672243 (Open Web Text)

Max Activating Token Index: 1023

Text #1

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.5557. Min Act: -0.1700

Data Index: 8574544 (Open Web Text)

Max Activating Token Index: 1023

Text #2

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.5444. Min Act: -0.1700

Data Index: 7528010 (Open Web Text)

Max Activating Token Index: 1023

Text #3

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4810. Min Act: -0.1700

Data Index: 1897417 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4595. Min Act: -0.1700

Data Index: 6401406 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4409. Min Act: -0.1700

Data Index: 4264744 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4472. Min Act: -0.1700

Data Index: 563951 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4297. Min Act: -0.1700

Data Index: 7553278 (Open Web Text)

Max Activating Token Index: 1023

Text #8

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4208. Min Act: -0.1700

Data Index: 8577367 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4166. Min Act: -0.1700

Data Index: 4250042 (Open Web Text)

Max Activating Token Index: 1023

Text #10

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4112. Min Act: -0.1700

Data Index: 169142 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4088. Min Act: -0.1700

Data Index: 4374310 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.3896. Min Act: -0.1700

Data Index: 6040894 (Open Web Text)

Max Activating Token Index: 1023

Text #13

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4041. Min Act: -0.1700

Data Index: 5636145 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4047. Min Act: -0.1700

Data Index: 7377792 (Open Web Text)

Max Activating Token Index: 1023

Text #15

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.4031. Min Act: -0.1700

Data Index: 399878 (Open Web Text)

Max Activating Token Index: 1023

Text #16

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.3792. Min Act: -0.1700

Data Index: 5040277 (Open Web Text)

Max Activating Token Index: 1023

Text #17

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.3831. Min Act: -0.1700

Data Index: 7138237 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.3796. Min Act: -0.1700

Data Index: 306882 (Open Web Text)

Max Activating Token Index: 1023

Text #19

Max Range: 2.6375. Min Range: -2.6375

Max Act: 2.3932. Min Act: -0.1700

Data Index: 4834300 (Open Web Text)

Max Activating Token Index: 1023