Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2696 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1481. Min Range: -3.1481
Max Act: 3.1481. Min Act: -0.1700
Data Index: 5080242 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.9746. Min Act: -0.1700
Data Index: 4096755 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.8795. Min Act: -0.1700
Data Index: 8009458 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.8000. Min Act: -0.1700
Data Index: 163814 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.8000. Min Act: -0.1700
Data Index: 579184 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7681. Min Act: -0.1434
Data Index: 6769593 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7362. Min Act: -0.1700
Data Index: 1333507 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7362. Min Act: -0.1700
Data Index: 7222474 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7362. Min Act: -0.1700
Data Index: 5202978 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7042. Min Act: -0.1700
Data Index: 3635534 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7202. Min Act: -0.1700
Data Index: 6049554 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7202. Min Act: -0.1700
Data Index: 6399350 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7042. Min Act: -0.1700
Data Index: 7118358 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7202. Min Act: -0.1700
Data Index: 1599069 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.6882. Min Act: -0.1700
Data Index: 5261398 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.6722. Min Act: -0.1700
Data Index: 6977891 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.7042. Min Act: -0.1700
Data Index: 5340524 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.6882. Min Act: -0.1698
Data Index: 3576111 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.6722. Min Act: -0.1700
Data Index: 2510569 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1481. Min Range: -3.1481
Max Act: 2.6882. Min Act: -0.1700
Data Index: 252846 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19