Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3503 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.2722. Min Act: -0.1700
Data Index: 7238933 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.2409. Min Act: -0.1700
Data Index: 6769591 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.2409. Min Act: -0.1700
Data Index: 2149451 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.2097. Min Act: -0.1700
Data Index: 4390695 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.1784. Min Act: -0.1700
Data Index: 6466921 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.1159. Min Act: -0.1700
Data Index: 3883654 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.1159. Min Act: -0.1700
Data Index: 7730389 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0847. Min Act: -0.1700
Data Index: 6937010 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0534. Min Act: -0.1700
Data Index: 5253637 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0534. Min Act: -0.1700
Data Index: 2110316 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0534. Min Act: -0.1700
Data Index: 8236149 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2722. Min Range: -5.2722
Max Act: 4.9909. Min Act: -0.1700
Data Index: 3883653 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0222. Min Act: -0.1700
Data Index: 1023997 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0222. Min Act: -0.1700
Data Index: 3416194 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0222. Min Act: -0.1700
Data Index: 5101193 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0222. Min Act: -0.1700
Data Index: 8469977 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2722. Min Range: -5.2722
Max Act: 5.0222. Min Act: -0.1700
Data Index: 6736724 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2722. Min Range: -5.2722
Max Act: 4.9909. Min Act: -0.1700
Data Index: 2023471 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2722. Min Range: -5.2722
Max Act: 4.9909. Min Act: -0.1700
Data Index: 5794719 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2722. Min Range: -5.2722
Max Act: 4.9909. Min Act: -0.1700
Data Index: 1469521 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19