Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.3288. Min Act: -0.1700
Data Index: 1554457 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.2663. Min Act: -0.1700
Data Index: 4264913 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.1726. Min Act: -0.1700
Data Index: 662102 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.1726. Min Act: -0.1700
Data Index: 8246308 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.2038. Min Act: -0.1700
Data Index: 157787 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.1413. Min Act: -0.1700
Data Index: 162521 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.1413. Min Act: -0.1700
Data Index: 8337662 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.1101. Min Act: -0.1700
Data Index: 171420 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.1413. Min Act: -0.1700
Data Index: 792724 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.1101. Min Act: -0.1700
Data Index: 8463157 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.0788. Min Act: -0.1700
Data Index: 6928911 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.0788. Min Act: -0.1700
Data Index: 2125168 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.0476. Min Act: -0.1700
Data Index: 4932019 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.0163. Min Act: -0.1700
Data Index: 4127653 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3288. Min Range: -5.3288
Max Act: 5.0163. Min Act: -0.1700
Data Index: 5989102 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3288. Min Range: -5.3288
Max Act: 4.9851. Min Act: -0.1700
Data Index: 2639718 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3288. Min Range: -5.3288
Max Act: 4.9851. Min Act: -0.1700
Data Index: 1881803 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3288. Min Range: -5.3288
Max Act: 4.9851. Min Act: -0.1700
Data Index: 2639719 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3288. Min Range: -5.3288
Max Act: 4.9851. Min Act: -0.1700
Data Index: 5284049 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3288. Min Range: -5.3288
Max Act: 4.9851. Min Act: -0.1700
Data Index: 627359 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19