Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1055 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1174. Min Range: -5.1174
Max Act: 5.1174. Min Act: -0.1700
Data Index: 3934540 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.9924. Min Act: -0.1700
Data Index: 8110179 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.9924. Min Act: -0.1700
Data Index: 4981678 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.9612. Min Act: -0.1700
Data Index: 7171683 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.9299. Min Act: -0.1700
Data Index: 1382602 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.9299. Min Act: -0.1700
Data Index: 3260523 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.9299. Min Act: -0.1700
Data Index: 2994212 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8987. Min Act: -0.1700
Data Index: 7870844 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8987. Min Act: -0.1700
Data Index: 7728704 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8987. Min Act: -0.1700
Data Index: 3713385 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8674. Min Act: -0.1700
Data Index: 6561707 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8674. Min Act: -0.1700
Data Index: 3282408 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8362. Min Act: -0.1700
Data Index: 5245184 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8362. Min Act: -0.1700
Data Index: 3899597 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8049. Min Act: -0.1700
Data Index: 2876142 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8362. Min Act: -0.1700
Data Index: 6749586 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8049. Min Act: -0.1700
Data Index: 4015970 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.8049. Min Act: -0.1700
Data Index: 2736827 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.7424. Min Act: -0.1700
Data Index: 2114953 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1174. Min Range: -5.1174
Max Act: 4.7737. Min Act: -0.1700
Data Index: 5286785 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19