Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4535 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.8130. Min Act: -0.1700
Data Index: 5721911 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.6567. Min Act: -0.1700
Data Index: 3168360 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4067. Min Act: -0.1700
Data Index: 8195445 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.4380. Min Act: -0.1700
Data Index: 3929463 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3442. Min Act: -0.1700
Data Index: 7453681 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3442. Min Act: -0.1700
Data Index: 2841569 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3442. Min Act: -0.1700
Data Index: 7506634 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3130. Min Act: -0.1700
Data Index: 5356184 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.3130. Min Act: -0.1700
Data Index: 6041546 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2817. Min Act: -0.1700
Data Index: 5659434 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2505. Min Act: -0.1700
Data Index: 6442632 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2505. Min Act: -0.1700
Data Index: 8687373 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2192. Min Act: -0.1700
Data Index: 4490906 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2192. Min Act: -0.1700
Data Index: 5510426 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2192. Min Act: -0.1700
Data Index: 4242279 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.2192. Min Act: -0.1700
Data Index: 351976 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.1880. Min Act: -0.1700
Data Index: 3960832 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.1880. Min Act: -0.1700
Data Index: 6948437 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.1567. Min Act: -0.1700
Data Index: 7866054 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8130. Min Range: -5.8130
Max Act: 5.1567. Min Act: -0.1700
Data Index: 7397177 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19