Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3698. Min Range: -6.3698
Max Act: 6.3698. Min Act: -0.1700
Data Index: 2467777 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3698. Min Range: -6.3698
Max Act: 6.1823. Min Act: -0.1700
Data Index: 4245380 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3698. Min Range: -6.3698
Max Act: 6.1510. Min Act: -0.1700
Data Index: 5041985 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3698. Min Range: -6.3698
Max Act: 6.1510. Min Act: -0.1700
Data Index: 3855586 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3698. Min Range: -6.3698
Max Act: 6.0260. Min Act: -0.1700
Data Index: 3194070 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.9635. Min Act: -0.1700
Data Index: 3670049 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.9948. Min Act: -0.1700
Data Index: 3687893 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.9948. Min Act: -0.1700
Data Index: 3602914 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.9635. Min Act: -0.1700
Data Index: 7099230 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.9323. Min Act: -0.1700
Data Index: 3531070 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.9010. Min Act: -0.1700
Data Index: 8088687 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.8698. Min Act: -0.1700
Data Index: 3612873 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.8698. Min Act: -0.1700
Data Index: 1894322 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.8385. Min Act: -0.1700
Data Index: 4416013 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.8073. Min Act: -0.1700
Data Index: 2121035 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.7760. Min Act: -0.1700
Data Index: 2367203 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.8073. Min Act: -0.1700
Data Index: 8680680 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.7760. Min Act: -0.1700
Data Index: 2970944 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.7760. Min Act: -0.1700
Data Index: 2193313 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3698. Min Range: -6.3698
Max Act: 5.8073. Min Act: -0.1700
Data Index: 7186236 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19