Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3101 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.9472. Min Act: -0.1700
Data Index: 7390342 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.9630. Min Act: -0.1700
Data Index: 7142262 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.9630. Min Act: -0.1700
Data Index: 2355674 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.9155. Min Act: -0.1700
Data Index: 7181251 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8838. Min Act: -0.1700
Data Index: 4026200 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8838. Min Act: -0.1700
Data Index: 4910500 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8520. Min Act: -0.1700
Data Index: 3798548 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8679. Min Act: -0.1700
Data Index: 5362709 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8361. Min Act: -0.1700
Data Index: 8507373 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8361. Min Act: -0.1700
Data Index: 4648051 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8361. Min Act: -0.1700
Data Index: 6372465 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8361. Min Act: -0.1700
Data Index: 4541670 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8202. Min Act: -0.1700
Data Index: 6254255 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8043. Min Act: -0.1700
Data Index: 4152370 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.7884. Min Act: -0.1700
Data Index: 3321613 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.8043. Min Act: -0.1700
Data Index: 7601781 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.7884. Min Act: -0.1700
Data Index: 3568425 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.7724. Min Act: -0.1700
Data Index: 1777221 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.7724. Min Act: -0.1700
Data Index: 7123524 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9630. Min Range: -2.9630
Max Act: 2.7884. Min Act: -0.1700
Data Index: 6550546 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19