Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3761 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.3506. Min Act: -0.1700
Data Index: 3726281 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.1631. Min Act: -0.1700
Data Index: 376040 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.1631. Min Act: -0.1700
Data Index: 2847258 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.1006. Min Act: -0.1700
Data Index: 1278909 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.1006. Min Act: -0.1700
Data Index: 2250306 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.1006. Min Act: -0.1700
Data Index: 4057020 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.0381. Min Act: -0.1700
Data Index: 316886 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.0381. Min Act: -0.1700
Data Index: 2921248 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3506. Min Range: -9.3506
Max Act: 9.0381. Min Act: -0.1700
Data Index: 8443993 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.9131. Min Act: -0.1700
Data Index: 4930686 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.9756. Min Act: -0.1700
Data Index: 1565338 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.9131. Min Act: -0.1700
Data Index: 2294717 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.9131. Min Act: -0.1700
Data Index: 7168297 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.9131. Min Act: -0.1700
Data Index: 2054206 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.9131. Min Act: -0.1700
Data Index: 1044188 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.9131. Min Act: -0.1700
Data Index: 2640352 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.8506. Min Act: -0.1700
Data Index: 4546025 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.8506. Min Act: -0.1700
Data Index: 3553631 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.8506. Min Act: -0.1700
Data Index: 1264639 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3506. Min Range: -9.3506
Max Act: 8.7881. Min Act: -0.1700
Data Index: 859283 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19