Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3998 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1940. Min Range: -7.1940
Max Act: 7.1940. Min Act: -0.1700
Data Index: 7301209 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.9753. Min Act: -0.1700
Data Index: 7487147 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.5378. Min Act: -0.1700
Data Index: 3780060 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.4753. Min Act: -0.1700
Data Index: 6954945 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.5065. Min Act: -0.1700
Data Index: 8666607 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.4440. Min Act: -0.1700
Data Index: 1489882 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.4440. Min Act: -0.1700
Data Index: 8656606 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.4128. Min Act: -0.1700
Data Index: 5240493 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.4128. Min Act: -0.1700
Data Index: 1972030 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.3815. Min Act: -0.1700
Data Index: 2512289 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.3815. Min Act: -0.1700
Data Index: 1800348 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.3503. Min Act: -0.1700
Data Index: 2455298 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.3190. Min Act: -0.1700
Data Index: 6087528 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.3190. Min Act: -0.1700
Data Index: 5614122 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.2878. Min Act: -0.1700
Data Index: 1521861 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.2565. Min Act: -0.1700
Data Index: 5978632 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.3190. Min Act: -0.1700
Data Index: 5756728 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.2565. Min Act: -0.1700
Data Index: 1380991 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.2565. Min Act: -0.1700
Data Index: 2032888 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1940. Min Range: -7.1940
Max Act: 6.2565. Min Act: -0.1700
Data Index: 1374157 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19