Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5534 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0048. Min Range: -6.0048
Max Act: 6.0048. Min Act: -0.1700
Data Index: 6046633 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0048. Min Range: -6.0048
Max Act: 6.0048. Min Act: -0.1700
Data Index: 2959574 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.9735. Min Act: -0.1700
Data Index: 249823 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.8798. Min Act: -0.1700
Data Index: 1666364 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.8485. Min Act: -0.1700
Data Index: 1501880 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.8173. Min Act: -0.1700
Data Index: 1855600 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7860. Min Act: -0.1700
Data Index: 1567514 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7860. Min Act: -0.1700
Data Index: 895355 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7860. Min Act: -0.1700
Data Index: 7614473 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7548. Min Act: -0.1700
Data Index: 6428647 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7860. Min Act: -0.1700
Data Index: 940198 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7548. Min Act: -0.1700
Data Index: 3009968 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7235. Min Act: -0.1700
Data Index: 4243411 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7235. Min Act: -0.1700
Data Index: 7107795 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.7235. Min Act: -0.1700
Data Index: 7980246 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.6923. Min Act: -0.1700
Data Index: 940194 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.6923. Min Act: -0.1700
Data Index: 5950205 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.6610. Min Act: -0.1700
Data Index: 7346212 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.6610. Min Act: -0.1700
Data Index: 193086 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0048. Min Range: -6.0048
Max Act: 5.6298. Min Act: -0.1700
Data Index: 1925954 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19