Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.2999. Min Act: -0.1694
Data Index: 8023366 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.2057. Min Act: -0.1699
Data Index: 7457206 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1585. Min Act: -0.1700
Data Index: 6062950 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1585. Min Act: -0.1700
Data Index: 4540736 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1742. Min Act: -0.1700
Data Index: 3591044 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1427. Min Act: -0.1700
Data Index: 1319278 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1270. Min Act: -0.1700
Data Index: 1306345 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1270. Min Act: -0.1700
Data Index: 4444503 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1270. Min Act: -0.1700
Data Index: 447769 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.1112. Min Act: -0.1700
Data Index: 3356190 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0955. Min Act: -0.1700
Data Index: 445587 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0955. Min Act: -0.1699
Data Index: 1399429 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0797. Min Act: -0.1700
Data Index: 4932782 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0797. Min Act: -0.1700
Data Index: 1746668 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0797. Min Act: -0.1700
Data Index: 1500818 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0797. Min Act: -0.1700
Data Index: 3405064 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0639. Min Act: -0.1699
Data Index: 6545473 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0797. Min Act: -0.1700
Data Index: 1207692 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0639. Min Act: -0.1694
Data Index: 7896815 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2999. Min Range: -3.2999
Max Act: 3.0639. Min Act: -0.1700
Data Index: 3395298 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19