Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 678 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.2750. Min Act: -0.1700
Data Index: 4158618 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.2438. Min Act: -0.1700
Data Index: 4739573 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.2438. Min Act: -0.1700
Data Index: 6535190 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.1813. Min Act: -0.1700
Data Index: 6240399 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.2125. Min Act: -0.1700
Data Index: 8218962 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.2438. Min Act: -0.1700
Data Index: 6084862 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.1500. Min Act: -0.1700
Data Index: 1277615 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.1500. Min Act: -0.1700
Data Index: 8462258 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.1500. Min Act: -0.1700
Data Index: 2628657 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2750. Min Range: -5.2750
Max Act: 5.0563. Min Act: -0.1700
Data Index: 8701798 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9938. Min Act: -0.1700
Data Index: 76289 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9625. Min Act: -0.1700
Data Index: 6803092 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9625. Min Act: -0.1700
Data Index: 672290 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9625. Min Act: -0.1700
Data Index: 6515982 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9625. Min Act: -0.1700
Data Index: 7751698 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9625. Min Act: -0.1700
Data Index: 436547 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9313. Min Act: -0.1700
Data Index: 3371826 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9625. Min Act: -0.1700
Data Index: 4925135 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9000. Min Act: -0.1700
Data Index: 6699834 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2750. Min Range: -5.2750
Max Act: 4.9000. Min Act: -0.1700
Data Index: 5795214 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19