Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1595 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.6597. Min Act: -0.1700
Data Index: 7588368 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.4410. Min Act: -0.1700
Data Index: 7000905 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.3160. Min Act: -0.1700
Data Index: 5699490 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.2847. Min Act: -0.1700
Data Index: 6770757 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.2535. Min Act: -0.1700
Data Index: 4373133 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.2535. Min Act: -0.1700
Data Index: 8111766 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.2535. Min Act: -0.1700
Data Index: 462350 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.2222. Min Act: -0.1700
Data Index: 5144583 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.2222. Min Act: -0.1700
Data Index: 8538039 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.1597. Min Act: -0.1700
Data Index: 692955 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.1597. Min Act: -0.1700
Data Index: 6745365 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.1285. Min Act: -0.1700
Data Index: 1324590 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.1285. Min Act: -0.1700
Data Index: 4203594 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.0972. Min Act: -0.1700
Data Index: 6489873 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.0660. Min Act: -0.1700
Data Index: 4519696 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.0660. Min Act: -0.1700
Data Index: 4723253 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.0660. Min Act: -0.1700
Data Index: 155460 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.0660. Min Act: -0.1700
Data Index: 1019246 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.0035. Min Act: -0.1700
Data Index: 1346716 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6597. Min Range: -5.6597
Max Act: 5.0035. Min Act: -0.1700
Data Index: 2866001 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19