Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1641 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.9765. Min Act: -0.1700
Data Index: 4104787 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.6952. Min Act: -0.1700
Data Index: 710375 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.6639. Min Act: -0.1700
Data Index: 5108113 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.6639. Min Act: -0.1700
Data Index: 1000441 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.5702. Min Act: -0.1700
Data Index: 6654643 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.5702. Min Act: -0.1700
Data Index: 4198539 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.5389. Min Act: -0.1700
Data Index: 6461620 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.5389. Min Act: -0.1700
Data Index: 5419671 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.5389. Min Act: -0.1700
Data Index: 87437 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.5077. Min Act: -0.1700
Data Index: 1913793 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4764. Min Act: -0.1700
Data Index: 1720130 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4764. Min Act: -0.1700
Data Index: 2039378 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4452. Min Act: -0.1700
Data Index: 4259262 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4452. Min Act: -0.1700
Data Index: 8480860 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4452. Min Act: -0.1700
Data Index: 8120807 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4139. Min Act: -0.1700
Data Index: 87558 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4452. Min Act: -0.1700
Data Index: 6642338 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4452. Min Act: -0.1700
Data Index: 4755637 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.3827. Min Act: -0.1700
Data Index: 1747780 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9765. Min Range: -4.9765
Max Act: 4.4139. Min Act: -0.1700
Data Index: 2062877 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19