Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9773. Min Range: -7.9773
Max Act: 7.9773. Min Act: -0.1700
Data Index: 7633709 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9773. Min Range: -7.9773
Max Act: 7.8211. Min Act: -0.1700
Data Index: 2271999 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9773. Min Range: -7.9773
Max Act: 7.4148. Min Act: -0.1700
Data Index: 1463377 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9773. Min Range: -7.9773
Max Act: 7.3523. Min Act: -0.1700
Data Index: 4110647 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9773. Min Range: -7.9773
Max Act: 7.3523. Min Act: -0.1700
Data Index: 2272000 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9773. Min Range: -7.9773
Max Act: 7.3211. Min Act: -0.1700
Data Index: 5903069 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.9773. Min Act: -0.1700
Data Index: 5352579 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.9148. Min Act: -0.1700
Data Index: 5345271 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.8523. Min Act: -0.1700
Data Index: 83328 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.8836. Min Act: -0.1700
Data Index: 2182098 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.8211. Min Act: -0.1700
Data Index: 8104443 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.7898. Min Act: -0.1700
Data Index: 6464736 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.7586. Min Act: -0.1700
Data Index: 81598 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.7586. Min Act: -0.1700
Data Index: 777922 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.6961. Min Act: -0.1700
Data Index: 2931404 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.6961. Min Act: -0.1700
Data Index: 3673154 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.6961. Min Act: -0.1700
Data Index: 1320095 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.6336. Min Act: -0.1700
Data Index: 6049545 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.6336. Min Act: -0.1700
Data Index: 3200404 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9773. Min Range: -7.9773
Max Act: 6.6336. Min Act: -0.1700
Data Index: 5864988 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19