Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1315 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5554. Min Range: -8.5554
Max Act: 8.5554. Min Act: -0.1700
Data Index: 620622 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5554. Min Range: -8.5554
Max Act: 8.4929. Min Act: -0.1700
Data Index: 3018160 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5554. Min Range: -8.5554
Max Act: 8.3679. Min Act: -0.1700
Data Index: 3770294 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5554. Min Range: -8.5554
Max Act: 8.2429. Min Act: -0.1700
Data Index: 5109013 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5554. Min Range: -8.5554
Max Act: 8.2429. Min Act: -0.1700
Data Index: 5667423 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5554. Min Range: -8.5554
Max Act: 8.1804. Min Act: -0.1700
Data Index: 7608562 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5554. Min Range: -8.5554
Max Act: 8.0554. Min Act: -0.1700
Data Index: 3147294 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.9304. Min Act: -0.1700
Data Index: 6216462 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.9304. Min Act: -0.1700
Data Index: 3638349 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.9929. Min Act: -0.1700
Data Index: 1941767 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.9929. Min Act: -0.1700
Data Index: 2811416 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.9304. Min Act: -0.1700
Data Index: 3489743 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.9304. Min Act: -0.1700
Data Index: 1417133 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.9304. Min Act: -0.1700
Data Index: 447882 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.8679. Min Act: -0.1700
Data Index: 1812408 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.8679. Min Act: -0.1700
Data Index: 2106203 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.8679. Min Act: -0.1700
Data Index: 6116629 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.8679. Min Act: -0.1700
Data Index: 7511034 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.8054. Min Act: -0.1700
Data Index: 1413701 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5554. Min Range: -8.5554
Max Act: 7.8054. Min Act: -0.1700
Data Index: 6536204 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19