Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1527 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2744. Min Range: -5.2744
Max Act: 5.2744. Min Act: -0.1700
Data Index: 6534544 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2744. Min Range: -5.2744
Max Act: 5.2119. Min Act: -0.1700
Data Index: 2444561 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2744. Min Range: -5.2744
Max Act: 5.2119. Min Act: -0.1700
Data Index: 3701405 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2744. Min Range: -5.2744
Max Act: 5.2119. Min Act: -0.1700
Data Index: 5609597 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2744. Min Range: -5.2744
Max Act: 5.1181. Min Act: -0.1700
Data Index: 4490323 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2744. Min Range: -5.2744
Max Act: 5.0556. Min Act: -0.1700
Data Index: 4916896 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.9931. Min Act: -0.1700
Data Index: 1281326 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.9931. Min Act: -0.1700
Data Index: 1438794 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.9619. Min Act: -0.1700
Data Index: 5114920 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.9619. Min Act: -0.1700
Data Index: 5296032 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.9306. Min Act: -0.1700
Data Index: 3262412 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.9306. Min Act: -0.1700
Data Index: 5373143 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.9306. Min Act: -0.1700
Data Index: 4040534 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.8994. Min Act: -0.1700
Data Index: 567110 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.8994. Min Act: -0.1700
Data Index: 4748779 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.8994. Min Act: -0.1700
Data Index: 8243071 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.8681. Min Act: -0.1700
Data Index: 7103839 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.8681. Min Act: -0.1700
Data Index: 8547249 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.8681. Min Act: -0.1700
Data Index: 4916895 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2744. Min Range: -5.2744
Max Act: 4.8369. Min Act: -0.1700
Data Index: 1031825 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19