Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4572 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0213. Min Range: -6.0213
Max Act: 6.0213. Min Act: -0.1700
Data Index: 4199135 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.7400. Min Act: -0.1700
Data Index: 7240219 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.7400. Min Act: -0.1700
Data Index: 11235 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.7088. Min Act: -0.1700
Data Index: 8112752 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.5838. Min Act: -0.1700
Data Index: 3810254 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.5213. Min Act: -0.1700
Data Index: 2859812 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.4588. Min Act: -0.1700
Data Index: 5735804 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.3650. Min Act: -0.1700
Data Index: 1084911 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.2400. Min Act: -0.1700
Data Index: 976682 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.2400. Min Act: -0.1700
Data Index: 4543843 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.2400. Min Act: -0.1700
Data Index: 4651058 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.2088. Min Act: -0.1700
Data Index: 937897 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.2088. Min Act: -0.1700
Data Index: 7520983 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.2088. Min Act: -0.1700
Data Index: 6467739 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.2088. Min Act: -0.1700
Data Index: 5054022 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.1775. Min Act: -0.1700
Data Index: 2670223 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.1775. Min Act: -0.1700
Data Index: 5352446 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.1463. Min Act: -0.1700
Data Index: 2549920 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.1775. Min Act: -0.1700
Data Index: 4023488 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0213. Min Range: -6.0213
Max Act: 5.1463. Min Act: -0.1700
Data Index: 2524877 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19