Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4242 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0450. Min Range: -5.0450
Max Act: 5.0450. Min Act: -0.1700
Data Index: 8599651 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.9200. Min Act: -0.1700
Data Index: 2397630 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.8575. Min Act: -0.1700
Data Index: 1794037 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.8262. Min Act: -0.1700
Data Index: 1840659 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7950. Min Act: -0.1700
Data Index: 4993753 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7637. Min Act: -0.1700
Data Index: 8742390 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.7012. Min Act: -0.1700
Data Index: 88451 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6699. Min Act: -0.1700
Data Index: 2291057 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6699. Min Act: -0.1700
Data Index: 7851544 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 5926357 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 4473470 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 8275426 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 3216242 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6387. Min Act: -0.1700
Data Index: 2356068 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6074. Min Act: -0.1700
Data Index: 7543185 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6074. Min Act: -0.1700
Data Index: 7409865 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6074. Min Act: -0.1700
Data Index: 5643059 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6074. Min Act: -0.1700
Data Index: 8383435 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6074. Min Act: -0.1700
Data Index: 5674978 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0450. Min Range: -5.0450
Max Act: 4.6074. Min Act: -0.1700
Data Index: 1342961 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19