Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3974 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3136. Min Range: -6.3136
Max Act: 6.3136. Min Act: -0.1700
Data Index: 1497066 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3136. Min Range: -6.3136
Max Act: 6.2199. Min Act: -0.1700
Data Index: 8088586 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3136. Min Range: -6.3136
Max Act: 6.0636. Min Act: -0.1700
Data Index: 3226114 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3136. Min Range: -6.3136
Max Act: 6.0011. Min Act: -0.1700
Data Index: 6138116 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3136. Min Range: -6.3136
Max Act: 6.0324. Min Act: -0.1700
Data Index: 22985 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.9699. Min Act: -0.1700
Data Index: 1267478 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3136. Min Range: -6.3136
Max Act: 6.0011. Min Act: -0.1700
Data Index: 2216850 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.9699. Min Act: -0.1700
Data Index: 8254602 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.9386. Min Act: -0.1700
Data Index: 7404055 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.9386. Min Act: -0.1700
Data Index: 8332571 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.9074. Min Act: -0.1700
Data Index: 8769086 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.9074. Min Act: -0.1700
Data Index: 8824237 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.8761. Min Act: -0.1700
Data Index: 1193598 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.7824. Min Act: -0.1700
Data Index: 1548301 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.8136. Min Act: -0.1700
Data Index: 6695848 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.8136. Min Act: -0.1700
Data Index: 6967333 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.8136. Min Act: -0.1700
Data Index: 6843348 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.8136. Min Act: -0.1700
Data Index: 2911471 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.8449. Min Act: -0.1700
Data Index: 2299737 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3136. Min Range: -6.3136
Max Act: 5.8136. Min Act: -0.1700
Data Index: 4175677 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19