Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.9150. Min Act: -0.1700
Data Index: 5271403 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.8837. Min Act: -0.1700
Data Index: 5811177 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.8525. Min Act: -0.1700
Data Index: 8691985 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.8212. Min Act: -0.1700
Data Index: 7362160 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.7900. Min Act: -0.1700
Data Index: 7904052 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.7587. Min Act: -0.1700
Data Index: 6032933 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6962. Min Act: -0.1700
Data Index: 3497374 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.7275. Min Act: -0.1700
Data Index: 4900491 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.7275. Min Act: -0.1700
Data Index: 6558706 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6962. Min Act: -0.1700
Data Index: 90061 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6962. Min Act: -0.1700
Data Index: 5416712 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6650. Min Act: -0.1699
Data Index: 6948284 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6337. Min Act: -0.1700
Data Index: 8678572 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6337. Min Act: -0.1700
Data Index: 5911030 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6025. Min Act: -0.1700
Data Index: 6364586 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6025. Min Act: -0.1700
Data Index: 8733019 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6025. Min Act: -0.1700
Data Index: 4126832 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6025. Min Act: -0.1700
Data Index: 3662863 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6025. Min Act: -0.1700
Data Index: 8657121 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9150. Min Range: -4.9150
Max Act: 4.6025. Min Act: -0.1700
Data Index: 2391350 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19