Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6256 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.8218. Min Act: -0.1700
Data Index: 801369 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.8218. Min Act: -0.1700
Data Index: 1612754 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.7436. Min Act: -0.1700
Data Index: 6424243 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.6810. Min Act: -0.1700
Data Index: 8214633 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.6810. Min Act: -0.1700
Data Index: 7844591 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.6341. Min Act: -0.1700
Data Index: 2709358 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5715. Min Act: -0.1700
Data Index: 1824917 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5402. Min Act: -0.1700
Data Index: 359067 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5402. Min Act: -0.1700
Data Index: 5450924 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5245. Min Act: -0.1700
Data Index: 723427 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5245. Min Act: -0.1700
Data Index: 7508195 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5245. Min Act: -0.1700
Data Index: 3530396 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5089. Min Act: -0.1700
Data Index: 2664629 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.5245. Min Act: -0.1700
Data Index: 1611715 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.4932. Min Act: -0.1700
Data Index: 2295315 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.4462. Min Act: -0.1700
Data Index: 6984159 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.4462. Min Act: -0.1700
Data Index: 8662016 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.4305. Min Act: -0.1700
Data Index: 3314743 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.4305. Min Act: -0.1700
Data Index: 5626129 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8218. Min Range: -3.8218
Max Act: 3.4305. Min Act: -0.1700
Data Index: 1158049 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19