Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.7088. Min Act: -0.1700
Data Index: 5458483 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.6619. Min Act: -0.1700
Data Index: 7476570 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.5210. Min Act: -0.1700
Data Index: 227919 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.5053. Min Act: -0.1700
Data Index: 2733307 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.4897. Min Act: -0.1700
Data Index: 3119372 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.4584. Min Act: -0.1700
Data Index: 7348837 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.4740. Min Act: -0.1700
Data Index: 800898 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.4427. Min Act: -0.1700
Data Index: 3469922 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.4113. Min Act: -0.1700
Data Index: 7945651 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3957. Min Act: -0.1700
Data Index: 5788753 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3957. Min Act: -0.1700
Data Index: 5413238 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3643. Min Act: -0.1700
Data Index: 6922146 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3800. Min Act: -0.1700
Data Index: 2110572 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3643. Min Act: -0.1700
Data Index: 1119895 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3643. Min Act: -0.1700
Data Index: 4806443 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3643. Min Act: -0.1700
Data Index: 4129784 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3486. Min Act: -0.1700
Data Index: 4733894 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3486. Min Act: -0.1700
Data Index: 7918235 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3329. Min Act: -0.1700
Data Index: 389339 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7088. Min Range: -3.7088
Max Act: 3.3486. Min Act: -0.1700
Data Index: 5273420 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19