Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1389. Min Range: -4.1389
Max Act: 4.1389. Min Act: -0.1700
Data Index: 6400595 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1389. Min Range: -4.1389
Max Act: 4.1076. Min Act: -0.1700
Data Index: 1062400 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.8575. Min Act: -0.1700
Data Index: 2316306 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.8575. Min Act: -0.1700
Data Index: 1878386 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.8262. Min Act: -0.1700
Data Index: 1878387 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7950. Min Act: -0.1700
Data Index: 4672651 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7950. Min Act: -0.1700
Data Index: 1448745 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7950. Min Act: -0.1700
Data Index: 72428 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7637. Min Act: -0.1700
Data Index: 6606923 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7637. Min Act: -0.1700
Data Index: 1878388 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7637. Min Act: -0.1700
Data Index: 1878390 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7011. Min Act: -0.1700
Data Index: 2072052 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7637. Min Act: -0.1700
Data Index: 6415693 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7011. Min Act: -0.1700
Data Index: 6111429 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.6698. Min Act: -0.1700
Data Index: 3684204 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.6698. Min Act: -0.1700
Data Index: 6947311 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.7011. Min Act: -0.1700
Data Index: 3946453 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.6698. Min Act: -0.1700
Data Index: 4594325 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.6698. Min Act: -0.1700
Data Index: 7253455 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1389. Min Range: -4.1389
Max Act: 3.6698. Min Act: -0.1700
Data Index: 691473 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19