Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1772. Min Range: -5.1772
Max Act: 5.1772. Min Act: -0.1700
Data Index: 932381 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1772. Min Range: -5.1772
Max Act: 5.1772. Min Act: -0.1700
Data Index: 5506570 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1772. Min Range: -5.1772
Max Act: 5.0522. Min Act: -0.1700
Data Index: 3322890 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.9897. Min Act: -0.1700
Data Index: 4669566 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.9585. Min Act: -0.1700
Data Index: 5506220 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.9272. Min Act: -0.1700
Data Index: 5387467 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8960. Min Act: -0.1700
Data Index: 7382511 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8960. Min Act: -0.1700
Data Index: 1464638 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8647. Min Act: -0.1700
Data Index: 5075492 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8647. Min Act: -0.1700
Data Index: 318441 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8647. Min Act: -0.1700
Data Index: 7091395 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8960. Min Act: -0.1700
Data Index: 368413 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8335. Min Act: -0.1700
Data Index: 1024228 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8335. Min Act: -0.1700
Data Index: 918792 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8335. Min Act: -0.1700
Data Index: 6903304 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8022. Min Act: -0.1700
Data Index: 4573834 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8022. Min Act: -0.1700
Data Index: 1385545 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.8022. Min Act: -0.1700
Data Index: 1028968 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.7710. Min Act: -0.1700
Data Index: 4609266 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1772. Min Range: -5.1772
Max Act: 4.7397. Min Act: -0.1700
Data Index: 601884 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19