Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 231 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4716. Min Range: -7.4716
Max Act: 7.4716. Min Act: -0.1700
Data Index: 3701931 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4716. Min Range: -7.4716
Max Act: 7.0966. Min Act: -0.1700
Data Index: 4249020 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4716. Min Range: -7.4716
Max Act: 7.0653. Min Act: -0.1700
Data Index: 452138 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4716. Min Range: -7.4716
Max Act: 7.0341. Min Act: -0.1700
Data Index: 4153047 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.9403. Min Act: -0.1700
Data Index: 5939864 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.9403. Min Act: -0.1700
Data Index: 3707382 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.9403. Min Act: -0.1700
Data Index: 561084 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.8778. Min Act: -0.1700
Data Index: 426942 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.8466. Min Act: -0.1700
Data Index: 4138842 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7841. Min Act: -0.1700
Data Index: 3603506 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.8153. Min Act: -0.1700
Data Index: 5065173 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.8153. Min Act: -0.1700
Data Index: 5555291 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7528. Min Act: -0.1700
Data Index: 1455674 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7841. Min Act: -0.1700
Data Index: 4947833 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7841. Min Act: -0.1700
Data Index: 6084936 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7528. Min Act: -0.1700
Data Index: 6956183 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7216. Min Act: -0.1700
Data Index: 2801475 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7216. Min Act: -0.1700
Data Index: 3997882 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.7216. Min Act: -0.1700
Data Index: 7344986 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4716. Min Range: -7.4716
Max Act: 6.6903. Min Act: -0.1700
Data Index: 1577533 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19