Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1446 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.9155. Min Act: -0.1700
Data Index: 355697 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.7905. Min Act: -0.1700
Data Index: 7089039 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.7280. Min Act: -0.1700
Data Index: 1578007 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.7280. Min Act: -0.1700
Data Index: 747366 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.7280. Min Act: -0.1700
Data Index: 909539 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.5405. Min Act: -0.1700
Data Index: 4244895 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.5405. Min Act: -0.1700
Data Index: 8316887 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.4155. Min Act: -0.1700
Data Index: 74635 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.3530. Min Act: -0.1700
Data Index: 2605833 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.3530. Min Act: -0.1700
Data Index: 6609719 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.3530. Min Act: -0.1700
Data Index: 8316880 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.3530. Min Act: -0.1700
Data Index: 2302216 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.2905. Min Act: -0.1700
Data Index: 3528311 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.2905. Min Act: -0.1700
Data Index: 4920018 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.2280. Min Act: -0.1700
Data Index: 8068933 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.2280. Min Act: -0.1700
Data Index: 2511253 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.2280. Min Act: -0.1700
Data Index: 1477463 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.1655. Min Act: -0.1700
Data Index: 2218143 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.1030. Min Act: -0.1700
Data Index: 2262206 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9155. Min Range: -9.9155
Max Act: 9.1655. Min Act: -0.1700
Data Index: 1762387 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19