Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.4325. Min Act: -0.1700
Data Index: 2997382 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.3700. Min Act: -0.1700
Data Index: 3758068 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.2763. Min Act: -0.1700
Data Index: 4708855 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.2450. Min Act: -0.1700
Data Index: 761954 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.1825. Min Act: -0.1700
Data Index: 1807491 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.1513. Min Act: -0.1700
Data Index: 1671534 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.1200. Min Act: -0.1700
Data Index: 4161440 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.1200. Min Act: -0.1700
Data Index: 4916240 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.0888. Min Act: -0.1700
Data Index: 7101791 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 407198 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 2143195 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.1200. Min Act: -0.1700
Data Index: 5696153 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 5696146 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.0263. Min Act: -0.1700
Data Index: 817206 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4325. Min Range: -6.4325
Max Act: 6.0575. Min Act: -0.1700
Data Index: 5479943 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4325. Min Range: -6.4325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 3259156 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4325. Min Range: -6.4325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 2445160 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4325. Min Range: -6.4325
Max Act: 5.9950. Min Act: -0.1700
Data Index: 2470753 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4325. Min Range: -6.4325
Max Act: 5.9638. Min Act: -0.1700
Data Index: 269195 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4325. Min Range: -6.4325
Max Act: 5.9325. Min Act: -0.1700
Data Index: 5695300 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19