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

Dataset: Open Web Text

Neuron 1065 in Layer 4

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: 3.3362. Min Range: -3.3362

Max Act: 3.3362. Min Act: -0.1700

Data Index: 3551668 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.3135. Min Act: -0.1700

Data Index: 7829217 (Open Web Text)

Max Activating Token Index: 70

Text #2

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.3043. Min Act: -0.1700

Data Index: 586587 (Open Web Text)

Max Activating Token Index: 146

Text #3

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2735. Min Act: -0.1700

Data Index: 469532 (Open Web Text)

Max Activating Token Index: 422

Text #4

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2910. Min Act: -0.1700

Data Index: 1450002 (Open Web Text)

Max Activating Token Index: 955

Text #5

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2719. Min Act: -0.1700

Data Index: 696802 (Open Web Text)

Max Activating Token Index: 181

Text #6

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2518. Min Act: -0.1700

Data Index: 864869 (Open Web Text)

Max Activating Token Index: 633

Text #7

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2532. Min Act: -0.1700

Data Index: 6024350 (Open Web Text)

Max Activating Token Index: 306

Text #8

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2291. Min Act: -0.1700

Data Index: 7143232 (Open Web Text)

Max Activating Token Index: 915

Text #9

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1916532 (Open Web Text)

Max Activating Token Index: 106

Text #10

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2157. Min Act: -0.1700

Data Index: 2034190 (Open Web Text)

Max Activating Token Index: 100

Text #11

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2287. Min Act: -0.1700

Data Index: 623912 (Open Web Text)

Max Activating Token Index: 144

Text #12

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2307. Min Act: -0.1700

Data Index: 2723240 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.1937. Min Act: -0.1700

Data Index: 2472573 (Open Web Text)

Max Activating Token Index: 734

Text #14

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2113. Min Act: -0.1700

Data Index: 2070198 (Open Web Text)

Max Activating Token Index: 267

Text #15

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.2061. Min Act: -0.1700

Data Index: 98092 (Open Web Text)

Max Activating Token Index: 964

Text #16

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.1912. Min Act: -0.1700

Data Index: 697074 (Open Web Text)

Max Activating Token Index: 148

Text #17

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.1958. Min Act: -0.1700

Data Index: 1769836 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.1716. Min Act: -0.1700

Data Index: 5838165 (Open Web Text)

Max Activating Token Index: 18

Text #19

Max Range: 3.3362. Min Range: -3.3362

Max Act: 3.1984. Min Act: -0.1700

Data Index: 5951944 (Open Web Text)

Max Activating Token Index: 123