Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3836. Min Range: -7.3836
Max Act: 7.3836. Min Act: -0.1700
Data Index: 7236198 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3836. Min Range: -7.3836
Max Act: 7.3523. Min Act: -0.1700
Data Index: 924073 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3836. Min Range: -7.3836
Max Act: 7.1961. Min Act: -0.1700
Data Index: 4399211 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3836. Min Range: -7.3836
Max Act: 7.0086. Min Act: -0.1700
Data Index: 6773902 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.7898. Min Act: -0.1700
Data Index: 5487953 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.7898. Min Act: -0.1700
Data Index: 4998424 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.7273. Min Act: -0.1700
Data Index: 1899571 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.6648. Min Act: -0.1700
Data Index: 946524 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.6961. Min Act: -0.1700
Data Index: 2864175 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.6336. Min Act: -0.1700
Data Index: 7341707 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.6023. Min Act: -0.1700
Data Index: 1279285 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5711. Min Act: -0.1700
Data Index: 5110345 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5711. Min Act: -0.1700
Data Index: 5271378 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5711. Min Act: -0.1700
Data Index: 8135681 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5398. Min Act: -0.1700
Data Index: 2691936 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5398. Min Act: -0.1700
Data Index: 1537920 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5711. Min Act: -0.1700
Data Index: 6307045 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5086. Min Act: -0.1700
Data Index: 5697734 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.5086. Min Act: -0.1700
Data Index: 1877853 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3836. Min Range: -7.3836
Max Act: 6.4773. Min Act: -0.1700
Data Index: 5461052 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19