Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6274 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2631. Min Range: -8.2631
Max Act: 8.2631. Min Act: -0.1700
Data Index: 6626834 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2631. Min Range: -8.2631
Max Act: 8.2006. Min Act: -0.1700
Data Index: 3857723 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2631. Min Range: -8.2631
Max Act: 8.1381. Min Act: -0.1700
Data Index: 1711784 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2631. Min Range: -8.2631
Max Act: 8.1381. Min Act: -0.1700
Data Index: 5792421 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2631. Min Range: -8.2631
Max Act: 8.0131. Min Act: -0.1700
Data Index: 7321677 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.9506. Min Act: -0.1700
Data Index: 3266288 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.8881. Min Act: -0.1700
Data Index: 8047658 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.8256. Min Act: -0.1700
Data Index: 3528670 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.8256. Min Act: -0.1700
Data Index: 1711787 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7319. Min Act: -0.1700
Data Index: 8369988 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7631. Min Act: -0.1700
Data Index: 3107358 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7944. Min Act: -0.1700
Data Index: 98627 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7319. Min Act: -0.1700
Data Index: 2221702 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7319. Min Act: -0.1700
Data Index: 4686971 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7319. Min Act: -0.1700
Data Index: 5953354 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7006. Min Act: -0.1700
Data Index: 4445884 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.7006. Min Act: -0.1700
Data Index: 6343084 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.6694. Min Act: -0.1700
Data Index: 8531123 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.6694. Min Act: -0.1700
Data Index: 3097830 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2631. Min Range: -8.2631
Max Act: 7.6381. Min Act: -0.1700
Data Index: 6518635 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19