Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1901 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.7830. Min Act: -0.1700
Data Index: 7483679 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.6580. Min Act: -0.1700
Data Index: 3025450 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.6267. Min Act: -0.1700
Data Index: 4466118 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.6267. Min Act: -0.1700
Data Index: 3711927 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.5330. Min Act: -0.1700
Data Index: 463821 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.5642. Min Act: -0.1700
Data Index: 2832671 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.5017. Min Act: -0.1700
Data Index: 5601788 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.4705. Min Act: -0.1700
Data Index: 1898305 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.4392. Min Act: -0.1700
Data Index: 1192651 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.4392. Min Act: -0.1700
Data Index: 8524706 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.4392. Min Act: -0.1700
Data Index: 4822169 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.4392. Min Act: -0.1700
Data Index: 5137578 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.4080. Min Act: -0.1700
Data Index: 1506653 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.4080. Min Act: -0.1700
Data Index: 4262055 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.3767. Min Act: -0.1700
Data Index: 2961224 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.3767. Min Act: -0.1700
Data Index: 3490232 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.3767. Min Act: -0.1700
Data Index: 3238178 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.3455. Min Act: -0.1700
Data Index: 1232127 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.3142. Min Act: -0.1700
Data Index: 1974429 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7830. Min Range: -6.7830
Max Act: 6.3142. Min Act: -0.1700
Data Index: 2680906 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19