Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.4280. Min Act: -0.1700
Data Index: 1116043 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.0842. Min Act: -0.1700
Data Index: 4685470 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4280. Min Range: -7.4280
Max Act: 7.0217. Min Act: -0.1700
Data Index: 3292579 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.9592. Min Act: -0.1700
Data Index: 1275250 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.9280. Min Act: -0.1700
Data Index: 2739352 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.9280. Min Act: -0.1700
Data Index: 4954083 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.7405. Min Act: -0.1700
Data Index: 785047 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.7092. Min Act: -0.1700
Data Index: 5718187 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.7405. Min Act: -0.1700
Data Index: 8186835 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6780. Min Act: -0.1700
Data Index: 3291861 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6467. Min Act: -0.1700
Data Index: 8300227 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6467. Min Act: -0.1700
Data Index: 4490366 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6467. Min Act: -0.1700
Data Index: 3079395 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6155. Min Act: -0.1700
Data Index: 2598121 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6155. Min Act: -0.1700
Data Index: 3264788 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6155. Min Act: -0.1700
Data Index: 4678091 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.6155. Min Act: -0.1700
Data Index: 7658478 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.5842. Min Act: -0.1700
Data Index: 1351738 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.5530. Min Act: -0.1700
Data Index: 2364606 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4280. Min Range: -7.4280
Max Act: 6.5530. Min Act: -0.1700
Data Index: 1152145 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19