Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2929 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.9884. Min Act: -0.1700
Data Index: 3849944 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.9571. Min Act: -0.1700
Data Index: 5492483 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.8946. Min Act: -0.1700
Data Index: 2273590 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.8320. Min Act: -0.1700
Data Index: 6994509 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.8633. Min Act: -0.1700
Data Index: 7982498 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.8008. Min Act: -0.1700
Data Index: 7369361 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7851. Min Act: -0.1700
Data Index: 516052 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7695. Min Act: -0.1700
Data Index: 2750594 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7539. Min Act: -0.1700
Data Index: 1301580 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7539. Min Act: -0.1700
Data Index: 8335976 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7695. Min Act: -0.1700
Data Index: 3649993 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7539. Min Act: -0.1700
Data Index: 6722633 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7382. Min Act: -0.1700
Data Index: 4551344 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7382. Min Act: -0.1700
Data Index: 6360832 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7382. Min Act: -0.1700
Data Index: 770498 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7226. Min Act: -0.1700
Data Index: 314301 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.7069. Min Act: -0.1700
Data Index: 7711232 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.6913. Min Act: -0.1700
Data Index: 1909142 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.6913. Min Act: -0.1700
Data Index: 7615198 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9884. Min Range: -3.9884
Max Act: 3.6600. Min Act: -0.1700
Data Index: 6795127 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19