Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2772 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0144. Min Range: -7.0144
Max Act: 7.0144. Min Act: -0.1700
Data Index: 7014851 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0144. Min Range: -7.0144
Max Act: 7.0144. Min Act: -0.1700
Data Index: 1443579 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.8582. Min Act: -0.1700
Data Index: 2782663 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.7957. Min Act: -0.1700
Data Index: 304957 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.7644. Min Act: -0.1700
Data Index: 2792833 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.6394. Min Act: -0.1700
Data Index: 8014821 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.6394. Min Act: -0.1700
Data Index: 2200970 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.6082. Min Act: -0.1700
Data Index: 1353971 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.5769. Min Act: -0.1700
Data Index: 6694636 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.5769. Min Act: -0.1700
Data Index: 2739394 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.5457. Min Act: -0.1700
Data Index: 2944137 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.5457. Min Act: -0.1700
Data Index: 5054029 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.5144. Min Act: -0.1700
Data Index: 5263837 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.5144. Min Act: -0.1700
Data Index: 291190 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.3894. Min Act: -0.1700
Data Index: 7351842 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.3894. Min Act: -0.1700
Data Index: 7802819 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.3894. Min Act: -0.1700
Data Index: 6436783 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.3582. Min Act: -0.1700
Data Index: 416260 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.3894. Min Act: -0.1700
Data Index: 5292102 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0144. Min Range: -7.0144
Max Act: 6.3582. Min Act: -0.1700
Data Index: 2472069 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #19