Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.6410. Min Act: -0.1700
Data Index: 8204790 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.5784. Min Act: -0.1700
Data Index: 2348085 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.5940. Min Act: -0.1700
Data Index: 3762266 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.5627. Min Act: -0.1700
Data Index: 5983907 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.5627. Min Act: -0.1700
Data Index: 2985784 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.5157. Min Act: -0.1700
Data Index: 2549817 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4844. Min Act: -0.1700
Data Index: 2810902 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4688. Min Act: -0.1700
Data Index: 2293122 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4844. Min Act: -0.1700
Data Index: 1019320 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4688. Min Act: -0.1700
Data Index: 2825904 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4531. Min Act: -0.1700
Data Index: 2763989 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4531. Min Act: -0.1700
Data Index: 3666666 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4531. Min Act: -0.1700
Data Index: 5509939 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4374. Min Act: -0.1700
Data Index: 7472100 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4374. Min Act: -0.1700
Data Index: 2561711 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4217. Min Act: -0.1700
Data Index: 5917596 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4217. Min Act: -0.1700
Data Index: 1801131 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4374. Min Act: -0.1700
Data Index: 790575 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4374. Min Act: -0.1700
Data Index: 6532865 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6410. Min Range: -3.6410
Max Act: 3.4217. Min Act: -0.1700
Data Index: 6570136 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19