Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5795 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0455. Min Range: -4.0455
Max Act: 4.0455. Min Act: -0.1700
Data Index: 5245061 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.8266. Min Act: -0.1700
Data Index: 7603094 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.6858. Min Act: -0.1700
Data Index: 5899611 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.6858. Min Act: -0.1700
Data Index: 4727239 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.6546. Min Act: -0.1700
Data Index: 5521028 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.6076. Min Act: -0.1700
Data Index: 6233928 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.5607. Min Act: -0.1700
Data Index: 2602489 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.5293. Min Act: -0.1700
Data Index: 1269979 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.5450. Min Act: -0.1700
Data Index: 6407952 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.5293. Min Act: -0.1700
Data Index: 353816 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.5137. Min Act: -0.1700
Data Index: 4660791 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.5137. Min Act: -0.1700
Data Index: 8086725 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.5137. Min Act: -0.1700
Data Index: 6626706 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.4980. Min Act: -0.1700
Data Index: 3053569 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.4980. Min Act: -0.1700
Data Index: 6525220 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.4667. Min Act: -0.1700
Data Index: 3014990 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.4510. Min Act: -0.1700
Data Index: 922793 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.4197. Min Act: -0.1700
Data Index: 8394611 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.4197. Min Act: -0.1700
Data Index: 6883923 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0455. Min Range: -4.0455
Max Act: 3.4197. Min Act: -0.1700
Data Index: 8025684 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19