Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2975 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.3029. Min Act: -0.1700
Data Index: 353013 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.2717. Min Act: -0.1700
Data Index: 5744917 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.2404. Min Act: -0.1700
Data Index: 7020483 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.1779. Min Act: -0.1700
Data Index: 6458093 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.1154. Min Act: -0.1700
Data Index: 6066549 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.1467. Min Act: -0.1700
Data Index: 6519902 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0529. Min Act: -0.1700
Data Index: 7170714 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0842. Min Act: -0.1700
Data Index: 6834265 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0842. Min Act: -0.1700
Data Index: 2607677 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0842. Min Act: -0.1700
Data Index: 2123101 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.1154. Min Act: -0.1700
Data Index: 7673407 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0842. Min Act: -0.1700
Data Index: 17414 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0529. Min Act: -0.1700
Data Index: 4983469 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0529. Min Act: -0.1700
Data Index: 3289336 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0529. Min Act: -0.1700
Data Index: 504035 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3029. Min Range: -4.3029
Max Act: 4.0216. Min Act: -0.1700
Data Index: 3714093 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3029. Min Range: -4.3029
Max Act: 3.9904. Min Act: -0.1700
Data Index: 860013 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3029. Min Range: -4.3029
Max Act: 3.9904. Min Act: -0.1700
Data Index: 6370976 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3029. Min Range: -4.3029
Max Act: 3.9904. Min Act: -0.1700
Data Index: 7710095 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3029. Min Range: -4.3029
Max Act: 3.9591. Min Act: -0.1700
Data Index: 3382655 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19