Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4482 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.7707. Min Act: -0.1700
Data Index: 2701127 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.7394. Min Act: -0.1700
Data Index: 723586 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.6769. Min Act: -0.1700
Data Index: 5679680 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.6769. Min Act: -0.1700
Data Index: 2099499 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.6457. Min Act: -0.1700
Data Index: 147857 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.6144. Min Act: -0.1700
Data Index: 2964377 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.6144. Min Act: -0.1700
Data Index: 4966362 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.5519. Min Act: -0.1700
Data Index: 7150312 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.4894. Min Act: -0.1700
Data Index: 4605339 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.4582. Min Act: -0.1700
Data Index: 281526 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3957. Min Act: -0.1700
Data Index: 261206 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.4269. Min Act: -0.1700
Data Index: 8509393 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3957. Min Act: -0.1700
Data Index: 1914511 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3957. Min Act: -0.1700
Data Index: 6224044 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3644. Min Act: -0.1700
Data Index: 6997656 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3644. Min Act: -0.1700
Data Index: 6604666 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3957. Min Act: -0.1700
Data Index: 3219015 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3644. Min Act: -0.1700
Data Index: 4780150 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3644. Min Act: -0.1700
Data Index: 4326993 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7707. Min Range: -5.7707
Max Act: 5.3332. Min Act: -0.1700
Data Index: 4126975 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19