Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.6716. Min Act: -0.1700
Data Index: 392134 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.5466. Min Act: -0.1700
Data Index: 6430931 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.5466. Min Act: -0.1700
Data Index: 7135537 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4841. Min Act: -0.1700
Data Index: 8332272 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4841. Min Act: -0.1700
Data Index: 8398471 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4841. Min Act: -0.1700
Data Index: 6554405 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4841. Min Act: -0.1700
Data Index: 3673508 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4216. Min Act: -0.1700
Data Index: 3105547 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4216. Min Act: -0.1700
Data Index: 8826512 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4216. Min Act: -0.1700
Data Index: 4596569 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.4216. Min Act: -0.1700
Data Index: 7471548 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.3591. Min Act: -0.1700
Data Index: 1632926 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.3591. Min Act: -0.1700
Data Index: 6761188 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.3591. Min Act: -0.1700
Data Index: 5161325 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.3591. Min Act: -0.1700
Data Index: 2254749 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.3591. Min Act: -0.1700
Data Index: 5891232 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.3591. Min Act: -0.1700
Data Index: 6337254 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.2966. Min Act: -0.1700
Data Index: 6334774 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.3591. Min Act: -0.1700
Data Index: 498924 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6716. Min Range: -7.6716
Max Act: 7.2654. Min Act: -0.1700
Data Index: 2425772 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19