Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 687 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3717. Min Range: -6.3717
Max Act: 6.3717. Min Act: -0.1700
Data Index: 2413010 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.8092. Min Act: -0.1700
Data Index: 4316754 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.7779. Min Act: -0.1700
Data Index: 1065999 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.7467. Min Act: -0.1700
Data Index: 5890055 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.7467. Min Act: -0.1700
Data Index: 4762917 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.7467. Min Act: -0.1700
Data Index: 3462609 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.7154. Min Act: -0.1700
Data Index: 2356065 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6842. Min Act: -0.1700
Data Index: 7134698 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 6328516 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 8176023 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 4987435 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 674400 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 758631 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 8809971 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 499040 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6217. Min Act: -0.1700
Data Index: 449943 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6529. Min Act: -0.1700
Data Index: 3972167 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.6217. Min Act: -0.1700
Data Index: 6820223 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.5904. Min Act: -0.1700
Data Index: 4559649 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3717. Min Range: -6.3717
Max Act: 5.5592. Min Act: -0.1700
Data Index: 8106326 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19