Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5227 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.7330. Min Act: -0.1700
Data Index: 5210217 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.6704. Min Act: -0.1700
Data Index: 2930462 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.7017. Min Act: -0.1700
Data Index: 7765577 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.6704. Min Act: -0.1700
Data Index: 5606132 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.6391. Min Act: -0.1700
Data Index: 7877487 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.6391. Min Act: -0.1700
Data Index: 5070917 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.6078. Min Act: -0.1700
Data Index: 6639818 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.6078. Min Act: -0.1700
Data Index: 1669032 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5765. Min Act: -0.1700
Data Index: 8062638 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5765. Min Act: -0.1700
Data Index: 2176102 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5452. Min Act: -0.1700
Data Index: 6665629 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5765. Min Act: -0.1700
Data Index: 3827022 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5452. Min Act: -0.1700
Data Index: 7605605 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5139. Min Act: -0.1700
Data Index: 8821304 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5139. Min Act: -0.1700
Data Index: 7754427 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5452. Min Act: -0.1700
Data Index: 3726433 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.5139. Min Act: -0.1700
Data Index: 4159575 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4826. Min Act: -0.1700
Data Index: 5199535 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4826. Min Act: -0.1700
Data Index: 5268710 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7330. Min Range: -3.7330
Max Act: 3.4826. Min Act: -0.1700
Data Index: 5535682 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19