Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1138. Min Range: -5.1138
Max Act: 5.1138. Min Act: -0.1700
Data Index: 6023837 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.7701. Min Act: -0.1700
Data Index: 4292957 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.7701. Min Act: -0.1700
Data Index: 1322206 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.7388. Min Act: -0.1700
Data Index: 4277013 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.7076. Min Act: -0.1700
Data Index: 539863 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.6451. Min Act: -0.1700
Data Index: 316401 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.6138. Min Act: -0.1700
Data Index: 397258 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5513. Min Act: -0.1700
Data Index: 740186 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5513. Min Act: -0.1700
Data Index: 5898632 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5826. Min Act: -0.1700
Data Index: 2884420 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5513. Min Act: -0.1700
Data Index: 3645421 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5513. Min Act: -0.1700
Data Index: 4095179 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5513. Min Act: -0.1700
Data Index: 5386230 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5201. Min Act: -0.1700
Data Index: 7566109 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5201. Min Act: -0.1700
Data Index: 5627709 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5201. Min Act: -0.1700
Data Index: 6093420 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.5201. Min Act: -0.1700
Data Index: 7695303 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.4576. Min Act: -0.1700
Data Index: 6253933 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.4888. Min Act: -0.1700
Data Index: 5607558 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1138. Min Range: -5.1138
Max Act: 4.4888. Min Act: -0.1700
Data Index: 5971863 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19