Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4647 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.8931. Min Act: -0.1700
Data Index: 3881766 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.7994. Min Act: -0.1700
Data Index: 8664252 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.6744. Min Act: -0.1700
Data Index: 5108082 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.6744. Min Act: -0.1700
Data Index: 4569201 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.6119. Min Act: -0.1700
Data Index: 3361437 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.5494. Min Act: -0.1700
Data Index: 7043990 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.5494. Min Act: -0.1700
Data Index: 3485770 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.5181. Min Act: -0.1700
Data Index: 4425247 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.5181. Min Act: -0.1700
Data Index: 3743971 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.4869. Min Act: -0.1700
Data Index: 2881318 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.4556. Min Act: -0.1700
Data Index: 984857 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3931. Min Act: -0.1700
Data Index: 7713568 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.4244. Min Act: -0.1700
Data Index: 5133879 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3931. Min Act: -0.1700
Data Index: 1347319 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3931. Min Act: -0.1700
Data Index: 188066 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3931. Min Act: -0.1700
Data Index: 4822026 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3619. Min Act: -0.1700
Data Index: 4822514 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3619. Min Act: -0.1700
Data Index: 396240 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3931. Min Act: -0.1700
Data Index: 6930292 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8931. Min Range: -5.8931
Max Act: 5.3619. Min Act: -0.1700
Data Index: 6476480 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19