Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4396 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.3616. Min Act: -0.1700
Data Index: 5358565 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.3304. Min Act: -0.1700
Data Index: 8362617 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2679. Min Act: -0.1700
Data Index: 4943617 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.2366. Min Act: -0.1700
Data Index: 783562 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1741. Min Act: -0.1700
Data Index: 7693793 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1741. Min Act: -0.1700
Data Index: 5222351 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1741. Min Act: -0.1700
Data Index: 2804312 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1741. Min Act: -0.1700
Data Index: 5963892 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1429. Min Act: -0.1700
Data Index: 2654822 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1429. Min Act: -0.1700
Data Index: 8194875 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.1116. Min Act: -0.1700
Data Index: 5054146 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.0804. Min Act: -0.1700
Data Index: 5105909 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.0804. Min Act: -0.1700
Data Index: 6833492 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.0491. Min Act: -0.1700
Data Index: 7283465 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.0179. Min Act: -0.1700
Data Index: 666255 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.0179. Min Act: -0.1700
Data Index: 4537964 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3616. Min Range: -5.3616
Max Act: 5.0179. Min Act: -0.1700
Data Index: 4260810 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3616. Min Range: -5.3616
Max Act: 4.9866. Min Act: -0.1700
Data Index: 7865531 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3616. Min Range: -5.3616
Max Act: 4.9554. Min Act: -0.1700
Data Index: 308852 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3616. Min Range: -5.3616
Max Act: 4.9554. Min Act: -0.1700
Data Index: 6701564 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19