Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1425. Min Range: -5.1425
Max Act: 5.1425. Min Act: -0.1700
Data Index: 5623115 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1425. Min Range: -5.1425
Max Act: 5.1425. Min Act: -0.1700
Data Index: 8117363 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1425. Min Range: -5.1425
Max Act: 5.1113. Min Act: -0.1700
Data Index: 1494274 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1425. Min Range: -5.1425
Max Act: 5.0488. Min Act: -0.1700
Data Index: 5618898 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1425. Min Range: -5.1425
Max Act: 5.0175. Min Act: -0.1700
Data Index: 1285821 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.9238. Min Act: -0.1700
Data Index: 4859039 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.9238. Min Act: -0.1700
Data Index: 5543248 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8925. Min Act: -0.1700
Data Index: 2171846 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8925. Min Act: -0.1700
Data Index: 3034357 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.9238. Min Act: -0.1700
Data Index: 1265133 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8613. Min Act: -0.1700
Data Index: 7077156 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8925. Min Act: -0.1700
Data Index: 5230514 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8613. Min Act: -0.1700
Data Index: 5171437 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8613. Min Act: -0.1700
Data Index: 3068021 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8613. Min Act: -0.1700
Data Index: 4779093 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8613. Min Act: -0.1700
Data Index: 1263076 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8300. Min Act: -0.1700
Data Index: 7761835 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8300. Min Act: -0.1700
Data Index: 7418387 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8300. Min Act: -0.1700
Data Index: 3701387 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1425. Min Range: -5.1425
Max Act: 4.8300. Min Act: -0.1700
Data Index: 3630652 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19