Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1528. Min Range: -5.1528
Max Act: 5.1528. Min Act: -0.1700
Data Index: 1275242 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1528. Min Range: -5.1528
Max Act: 5.1216. Min Act: -0.1700
Data Index: 7220834 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1528. Min Range: -5.1528
Max Act: 5.0903. Min Act: -0.1700
Data Index: 8356644 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1528. Min Range: -5.1528
Max Act: 5.0591. Min Act: -0.1700
Data Index: 2923653 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.9966. Min Act: -0.1700
Data Index: 6637899 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.9966. Min Act: -0.1700
Data Index: 1275243 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.9653. Min Act: -0.1700
Data Index: 6499474 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.9966. Min Act: -0.1700
Data Index: 5198170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.9653. Min Act: -0.1700
Data Index: 4377447 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.9341. Min Act: -0.1700
Data Index: 8682105 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.9028. Min Act: -0.1700
Data Index: 3430644 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8716. Min Act: -0.1700
Data Index: 2648422 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8716. Min Act: -0.1700
Data Index: 3113090 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8716. Min Act: -0.1700
Data Index: 7996072 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8716. Min Act: -0.1700
Data Index: 2219342 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8716. Min Act: -0.1700
Data Index: 1908800 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8403. Min Act: -0.1700
Data Index: 5198169 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8403. Min Act: -0.1700
Data Index: 5198168 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8403. Min Act: -0.1700
Data Index: 2964441 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1528. Min Range: -5.1528
Max Act: 4.8403. Min Act: -0.1700
Data Index: 2423737 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19