Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0532. Min Range: -7.0532
Max Act: 7.0220. Min Act: -0.1700
Data Index: 7657159 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0532. Min Range: -7.0532
Max Act: 7.0532. Min Act: -0.1700
Data Index: 7885327 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.9595. Min Act: -0.1700
Data Index: 355076 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.9595. Min Act: -0.1700
Data Index: 334832 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.9907. Min Act: -0.1700
Data Index: 6720724 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.9595. Min Act: -0.1700
Data Index: 4201858 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.9282. Min Act: -0.1700
Data Index: 20589 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.9282. Min Act: -0.1700
Data Index: 2895296 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8970. Min Act: -0.1700
Data Index: 4723122 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8970. Min Act: -0.1700
Data Index: 8767277 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8970. Min Act: -0.1700
Data Index: 6204947 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8657. Min Act: -0.1700
Data Index: 2507734 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8345. Min Act: -0.1700
Data Index: 1670618 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8345. Min Act: -0.1700
Data Index: 597530 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8032. Min Act: -0.1700
Data Index: 2074178 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8032. Min Act: -0.1700
Data Index: 2686686 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8032. Min Act: -0.1700
Data Index: 4991824 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.7720. Min Act: -0.1700
Data Index: 682822 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.7720. Min Act: -0.1700
Data Index: 4651755 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.8032. Min Act: -0.1700
Data Index: 7427435 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19