Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 621 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.8635. Min Act: -0.1700
Data Index: 5996700 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.8322. Min Act: -0.1700
Data Index: 5994300 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.8635. Min Act: -0.1700
Data Index: 5996723 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.8010. Min Act: -0.1700
Data Index: 7024969 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.7697. Min Act: -0.1700
Data Index: 7632725 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.7072. Min Act: -0.1700
Data Index: 5876951 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.6760. Min Act: -0.1700
Data Index: 4772593 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.6760. Min Act: -0.1700
Data Index: 8308613 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.6447. Min Act: -0.1700
Data Index: 3227842 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.6447. Min Act: -0.1700
Data Index: 1063130 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.6447. Min Act: -0.1700
Data Index: 5749096 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.6135. Min Act: -0.1700
Data Index: 5813747 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.5510. Min Act: -0.1700
Data Index: 68728 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.5822. Min Act: -0.1700
Data Index: 3656524 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.5510. Min Act: -0.1700
Data Index: 693137 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.5510. Min Act: -0.1700
Data Index: 5749089 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.5197. Min Act: -0.1700
Data Index: 6164885 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.5197. Min Act: -0.1700
Data Index: 4535209 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.4885. Min Act: -0.1700
Data Index: 5996714 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8635. Min Range: -7.8635
Max Act: 7.4260. Min Act: -0.1700
Data Index: 5877709 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19