Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2286. Min Range: -5.2286
Max Act: 5.2286. Min Act: -0.1700
Data Index: 2857049 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2286. Min Range: -5.2286
Max Act: 5.1974. Min Act: -0.1700
Data Index: 6424602 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2286. Min Range: -5.2286
Max Act: 5.1036. Min Act: -0.1700
Data Index: 5858155 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2286. Min Range: -5.2286
Max Act: 5.0724. Min Act: -0.1700
Data Index: 3983092 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2286. Min Range: -5.2286
Max Act: 5.0411. Min Act: -0.1700
Data Index: 7449039 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2286. Min Range: -5.2286
Max Act: 5.0099. Min Act: -0.1700
Data Index: 5936463 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2286. Min Range: -5.2286
Max Act: 5.0099. Min Act: -0.1700
Data Index: 813572 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.9474. Min Act: -0.1700
Data Index: 2819857 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.9474. Min Act: -0.1700
Data Index: 931060 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.9161. Min Act: -0.1700
Data Index: 643528 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8849. Min Act: -0.1700
Data Index: 204055 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8849. Min Act: -0.1700
Data Index: 5838716 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8849. Min Act: -0.1700
Data Index: 4042853 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8536. Min Act: -0.1700
Data Index: 7023619 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8224. Min Act: -0.1700
Data Index: 2059429 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8224. Min Act: -0.1700
Data Index: 7226059 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8224. Min Act: -0.1700
Data Index: 8557840 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8224. Min Act: -0.1700
Data Index: 5552481 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.8224. Min Act: -0.1700
Data Index: 6831835 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2286. Min Range: -5.2286
Max Act: 4.7599. Min Act: -0.1700
Data Index: 1188068 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19