Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2791 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.7469. Min Act: -0.1700
Data Index: 4815374 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.7469. Min Act: -0.1700
Data Index: 4683758 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.6531. Min Act: -0.1700
Data Index: 3722936 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.6219. Min Act: -0.1700
Data Index: 4141156 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.5281. Min Act: -0.1700
Data Index: 2909511 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.5281. Min Act: -0.1700
Data Index: 8529670 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.5281. Min Act: -0.1700
Data Index: 8541789 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4344. Min Act: -0.1700
Data Index: 4847276 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3719. Min Act: -0.1700
Data Index: 5876605 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.4031. Min Act: -0.1700
Data Index: 429840 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3719. Min Act: -0.1700
Data Index: 8436137 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3719. Min Act: -0.1700
Data Index: 8694660 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3094. Min Act: -0.1700
Data Index: 5972784 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3406. Min Act: -0.1700
Data Index: 6495225 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3406. Min Act: -0.1700
Data Index: 1349118 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3719. Min Act: -0.1700
Data Index: 1107756 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3406. Min Act: -0.1700
Data Index: 7575078 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3094. Min Act: -0.1700
Data Index: 6014932 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.3094. Min Act: -0.1700
Data Index: 321303 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7469. Min Range: -5.7469
Max Act: 5.2781. Min Act: -0.1700
Data Index: 2039872 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19