Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2305. Min Range: -6.2305
Max Act: 6.2305. Min Act: -0.1700
Data Index: 4086777 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2305. Min Range: -6.2305
Max Act: 6.0117. Min Act: -0.1700
Data Index: 3592461 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.9805. Min Act: -0.1700
Data Index: 4086782 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.9492. Min Act: -0.1700
Data Index: 4444526 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.9180. Min Act: -0.1700
Data Index: 7556347 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.8555. Min Act: -0.1700
Data Index: 1208688 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.8242. Min Act: -0.1700
Data Index: 4686596 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.7617. Min Act: -0.1700
Data Index: 56331 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.7930. Min Act: -0.1700
Data Index: 1937725 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.7617. Min Act: -0.1700
Data Index: 5628848 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6992. Min Act: -0.1700
Data Index: 140523 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.7305. Min Act: -0.1700
Data Index: 8242175 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.7305. Min Act: -0.1700
Data Index: 6567668 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6992. Min Act: -0.1700
Data Index: 5626130 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6680. Min Act: -0.1700
Data Index: 7310648 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6680. Min Act: -0.1700
Data Index: 6222702 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6367. Min Act: -0.1700
Data Index: 1287961 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6367. Min Act: -0.1700
Data Index: 6129993 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6055. Min Act: -0.1700
Data Index: 7211193 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2305. Min Range: -6.2305
Max Act: 5.6055. Min Act: -0.1700
Data Index: 6196062 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19