Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4654 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.8571. Min Act: -0.1700
Data Index: 216681 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.7320. Min Act: -0.1700
Data Index: 4753803 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.6850. Min Act: -0.1700
Data Index: 671230 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.7007. Min Act: -0.1700
Data Index: 7209753 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.6537. Min Act: -0.1700
Data Index: 8764419 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.6694. Min Act: -0.1700
Data Index: 3240178 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.6381. Min Act: -0.1700
Data Index: 1851909 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5911. Min Act: -0.1700
Data Index: 828965 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5755. Min Act: -0.1700
Data Index: 3054695 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5598. Min Act: -0.1700
Data Index: 576134 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5442. Min Act: -0.1700
Data Index: 6837208 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5442. Min Act: -0.1700
Data Index: 216371 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5442. Min Act: -0.1700
Data Index: 5718363 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5442. Min Act: -0.1700
Data Index: 8824837 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5598. Min Act: -0.1700
Data Index: 2608331 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5285. Min Act: -0.1700
Data Index: 3205670 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.5285. Min Act: -0.1700
Data Index: 3994705 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.4972. Min Act: -0.1700
Data Index: 3130491 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.4972. Min Act: -0.1700
Data Index: 977230 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8571. Min Range: -3.8571
Max Act: 3.4972. Min Act: -0.1700
Data Index: 5454017 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19