Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.2251. Min Act: -0.1700
Data Index: 1423180 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.1587. Min Act: -0.1700
Data Index: 5284345 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.1587. Min Act: -0.1700
Data Index: 5935249 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.1253. Min Act: -0.1700
Data Index: 5680384 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.1420. Min Act: -0.1700
Data Index: 5115807 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.1253. Min Act: -0.1700
Data Index: 1507645 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0919. Min Act: -0.1700
Data Index: 8293541 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0919. Min Act: -0.1700
Data Index: 3273372 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0751. Min Act: -0.1700
Data Index: 8636453 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0919. Min Act: -0.1700
Data Index: 6080342 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0583. Min Act: -0.1700
Data Index: 4218362 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0751. Min Act: -0.1700
Data Index: 3212289 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0751. Min Act: -0.1700
Data Index: 51975 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0583. Min Act: -0.1700
Data Index: 3320160 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0751. Min Act: -0.1700
Data Index: 1865558 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0751. Min Act: -0.1700
Data Index: 3292435 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0583. Min Act: -0.1700
Data Index: 5625262 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0583. Min Act: -0.1700
Data Index: 8149307 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0751. Min Act: -0.1700
Data Index: 593269 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2251. Min Range: -2.2251
Max Act: 2.0583. Min Act: -0.1700
Data Index: 8293545 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19