Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3224 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.9457. Min Act: -0.1700
Data Index: 5890984 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.8832. Min Act: -0.1700
Data Index: 1564298 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.8520. Min Act: -0.1700
Data Index: 2991034 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.8207. Min Act: -0.1700
Data Index: 421311 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.7582. Min Act: -0.1700
Data Index: 3099233 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6957. Min Act: -0.1700
Data Index: 7194272 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6957. Min Act: -0.1700
Data Index: 5488314 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6645. Min Act: -0.1700
Data Index: 7713041 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6332. Min Act: -0.1700
Data Index: 5475155 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6332. Min Act: -0.1700
Data Index: 2244489 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6332. Min Act: -0.1700
Data Index: 7464161 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6332. Min Act: -0.1700
Data Index: 7369852 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.6020. Min Act: -0.1700
Data Index: 1934625 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.5395. Min Act: -0.1700
Data Index: 4470833 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.5082. Min Act: -0.1700
Data Index: 2506228 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.5082. Min Act: -0.1700
Data Index: 5548357 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.4770. Min Act: -0.1700
Data Index: 5305121 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.4770. Min Act: -0.1700
Data Index: 4653365 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.4770. Min Act: -0.1700
Data Index: 456395 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9457. Min Range: -5.9457
Max Act: 5.4770. Min Act: -0.1700
Data Index: 5091882 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19