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

Dataset: Open Web Text

Neuron 1541 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: 3.6233. Min Range: -3.6233

Max Act: 3.6233. Min Act: -0.1700

Data Index: 4048400 (Open Web Text)

Max Activating Token Index: 491

Text #1

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.1843. Min Act: -0.1700

Data Index: 4420224 (Open Web Text)

Max Activating Token Index: 976

Text #2

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.1431. Min Act: -0.1700

Data Index: 178021 (Open Web Text)

Max Activating Token Index: 614

Text #3

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.1260. Min Act: -0.1700

Data Index: 5430533 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.0277. Min Act: -0.1700

Data Index: 1218117 (Open Web Text)

Max Activating Token Index: 50

Text #5

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.0297. Min Act: -0.1700

Data Index: 8672069 (Open Web Text)

Max Activating Token Index: 693

Text #6

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.0013. Min Act: -0.1700

Data Index: 6311516 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.0050. Min Act: -0.1700

Data Index: 650356 (Open Web Text)

Max Activating Token Index: 156

Text #8

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.0354. Min Act: -0.1700

Data Index: 44785 (Open Web Text)

Max Activating Token Index: 175

Text #9

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.9998. Min Act: -0.1700

Data Index: 311457 (Open Web Text)

Max Activating Token Index: 66

Text #10

Max Range: 3.6233. Min Range: -3.6233

Max Act: 3.0002. Min Act: -0.1700

Data Index: 2070709 (Open Web Text)

Max Activating Token Index: 34

Text #11

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.9945. Min Act: -0.1700

Data Index: 2295233 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.9887. Min Act: -0.1700

Data Index: 7152601 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.9545. Min Act: -0.1700

Data Index: 3628113 (Open Web Text)

Max Activating Token Index: 407

Text #14

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.9522. Min Act: -0.1700

Data Index: 4691062 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.8974. Min Act: -0.1700

Data Index: 5370776 (Open Web Text)

Max Activating Token Index: 763

Text #16

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.9207. Min Act: -0.1700

Data Index: 7475836 (Open Web Text)

Max Activating Token Index: 19

Text #17

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.8916. Min Act: -0.1700

Data Index: 3195786 (Open Web Text)

Max Activating Token Index: 14

Text #18

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.8934. Min Act: -0.1700

Data Index: 3123933 (Open Web Text)

Max Activating Token Index: 33

Text #19

Max Range: 3.6233. Min Range: -3.6233

Max Act: 2.9086. Min Act: -0.1700

Data Index: 3162079 (Open Web Text)

Max Activating Token Index: 444