Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2518 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2868. Min Range: -5.2868
Max Act: 5.2868. Min Act: -0.1700
Data Index: 5535017 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2868. Min Range: -5.2868
Max Act: 5.2243. Min Act: -0.1700
Data Index: 6162336 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2868. Min Range: -5.2868
Max Act: 5.1930. Min Act: -0.1700
Data Index: 5440105 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2868. Min Range: -5.2868
Max Act: 5.0368. Min Act: -0.1700
Data Index: 2610366 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.9743. Min Act: -0.1700
Data Index: 8205163 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.9118. Min Act: -0.1700
Data Index: 4294675 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.8493. Min Act: -0.1700
Data Index: 1567836 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.8180. Min Act: -0.1700
Data Index: 1748876 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.8180. Min Act: -0.1700
Data Index: 1344781 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.8180. Min Act: -0.1700
Data Index: 436545 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.7868. Min Act: -0.1700
Data Index: 4245459 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.7555. Min Act: -0.1700
Data Index: 5610654 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.7555. Min Act: -0.1700
Data Index: 3794008 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.7555. Min Act: -0.1700
Data Index: 3506917 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.7243. Min Act: -0.1700
Data Index: 2834062 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.6930. Min Act: -0.1700
Data Index: 8440820 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.7243. Min Act: -0.1700
Data Index: 3535820 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.6930. Min Act: -0.1700
Data Index: 7818628 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.6930. Min Act: -0.1700
Data Index: 3700952 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2868. Min Range: -5.2868
Max Act: 4.6930. Min Act: -0.1700
Data Index: 5073082 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19