Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3751 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.9155. Min Act: -0.1700
Data Index: 2630585 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.7280. Min Act: -0.1700
Data Index: 6146522 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.6343. Min Act: -0.1700
Data Index: 704598 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.5718. Min Act: -0.1700
Data Index: 6051724 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.3218. Min Act: -0.1700
Data Index: 3695638 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.3218. Min Act: -0.1700
Data Index: 4547085 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.2905. Min Act: -0.1700
Data Index: 3054724 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.2593. Min Act: -0.1700
Data Index: 5204902 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1968. Min Act: -0.1700
Data Index: 4379820 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1968. Min Act: -0.1700
Data Index: 2195436 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1343. Min Act: -0.1700
Data Index: 2724146 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1655. Min Act: -0.1700
Data Index: 24515 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1655. Min Act: -0.1700
Data Index: 8276085 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1655. Min Act: -0.1700
Data Index: 7760013 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1655. Min Act: -0.1700
Data Index: 8121874 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1343. Min Act: -0.1700
Data Index: 2667096 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1343. Min Act: -0.1700
Data Index: 1313016 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1030. Min Act: -0.1700
Data Index: 5880488 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.1030. Min Act: -0.1700
Data Index: 4051512 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9155. Min Range: -7.9155
Max Act: 7.0093. Min Act: -0.1700
Data Index: 4548425 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #19