Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 928 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5823. Min Range: -6.5823
Max Act: 6.5823. Min Act: -0.1700
Data Index: 4715344 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5823. Min Range: -6.5823
Max Act: 6.0511. Min Act: -0.1700
Data Index: 8095447 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5823. Min Range: -6.5823
Max Act: 6.0198. Min Act: -0.1700
Data Index: 5300213 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.9573. Min Act: -0.1700
Data Index: 459715 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.9261. Min Act: -0.1700
Data Index: 2166100 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.8323. Min Act: -0.1700
Data Index: 2795152 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.8011. Min Act: -0.1700
Data Index: 4009712 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.7698. Min Act: -0.1700
Data Index: 3836471 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7904376 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7738609 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.7698. Min Act: -0.1700
Data Index: 1443104 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.7698. Min Act: -0.1700
Data Index: 8804022 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.7698. Min Act: -0.1700
Data Index: 864751 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.7073. Min Act: -0.1700
Data Index: 6577114 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.7073. Min Act: -0.1700
Data Index: 4906155 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.7073. Min Act: -0.1700
Data Index: 6462685 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.6761. Min Act: -0.1700
Data Index: 433729 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.6448. Min Act: -0.1700
Data Index: 1612453 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.6448. Min Act: -0.1700
Data Index: 2684119 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5823. Min Range: -6.5823
Max Act: 5.6761. Min Act: -0.1700
Data Index: 3370618 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19