Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1539 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.9860. Min Act: -0.1700
Data Index: 3657019 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.9548. Min Act: -0.1700
Data Index: 8447210 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.9548. Min Act: -0.1700
Data Index: 5039593 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.8923. Min Act: -0.1700
Data Index: 411735 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.8610. Min Act: -0.1700
Data Index: 5728003 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.8923. Min Act: -0.1700
Data Index: 5831514 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.7673. Min Act: -0.1700
Data Index: 3633523 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.8298. Min Act: -0.1700
Data Index: 7920341 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.7985. Min Act: -0.1700
Data Index: 7701423 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.7673. Min Act: -0.1700
Data Index: 2367655 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.7360. Min Act: -0.1700
Data Index: 8085919 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.6735. Min Act: -0.1700
Data Index: 6013094 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.7048. Min Act: -0.1700
Data Index: 3111615 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.7048. Min Act: -0.1700
Data Index: 1059752 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.7048. Min Act: -0.1700
Data Index: 7123087 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.6423. Min Act: -0.1700
Data Index: 1380780 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.6423. Min Act: -0.1700
Data Index: 4597939 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.6110. Min Act: -0.1700
Data Index: 8211636 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.6423. Min Act: -0.1700
Data Index: 6569624 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9860. Min Range: -5.9860
Max Act: 5.6110. Min Act: -0.1700
Data Index: 3319303 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19