Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2858 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.4957. Min Act: -0.1700
Data Index: 4502215 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5205523 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.3394. Min Act: -0.1700
Data Index: 4453021 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.3082. Min Act: -0.1700
Data Index: 4612616 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.1832. Min Act: -0.1700
Data Index: 6200369 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.1519. Min Act: -0.1700
Data Index: 5997591 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.1519. Min Act: -0.1700
Data Index: 2287982 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.1207. Min Act: -0.1700
Data Index: 7967209 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.0894. Min Act: -0.1700
Data Index: 8809750 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4957. Min Range: -5.4957
Max Act: 5.0269. Min Act: -0.1700
Data Index: 2720712 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.9957. Min Act: -0.1700
Data Index: 4191463 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8707. Min Act: -0.1700
Data Index: 2620918 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8707. Min Act: -0.1700
Data Index: 2362576 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8082. Min Act: -0.1700
Data Index: 2625039 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8394. Min Act: -0.1700
Data Index: 4409045 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8082. Min Act: -0.1700
Data Index: 6969972 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8082. Min Act: -0.1700
Data Index: 4170723 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8082. Min Act: -0.1700
Data Index: 8815420 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.8082. Min Act: -0.1700
Data Index: 2943536 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4957. Min Range: -5.4957
Max Act: 4.7769. Min Act: -0.1700
Data Index: 1906624 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19