Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.4235. Min Act: -0.1700
Data Index: 6429975 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.3610. Min Act: -0.1700
Data Index: 5821786 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.2360. Min Act: -0.1700
Data Index: 116069 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.2360. Min Act: -0.1700
Data Index: 1709115 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.1422. Min Act: -0.1700
Data Index: 1396513 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.1735. Min Act: -0.1700
Data Index: 7511486 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.1110. Min Act: -0.1700
Data Index: 7445305 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.1110. Min Act: -0.1700
Data Index: 2399898 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.0485. Min Act: -0.1700
Data Index: 3921273 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.0485. Min Act: -0.1700
Data Index: 3968365 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4235. Min Range: -6.4235
Max Act: 6.0172. Min Act: -0.1700
Data Index: 4338632 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.9860. Min Act: -0.1700
Data Index: 622418 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.9547. Min Act: -0.1700
Data Index: 2862084 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.9860. Min Act: -0.1700
Data Index: 5315795 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.9235. Min Act: -0.1700
Data Index: 4505864 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.9547. Min Act: -0.1700
Data Index: 2565577 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.9235. Min Act: -0.1700
Data Index: 152375 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.9235. Min Act: -0.1700
Data Index: 1322624 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.8922. Min Act: -0.1700
Data Index: 8045791 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4235. Min Range: -6.4235
Max Act: 5.8922. Min Act: -0.1700
Data Index: 6869059 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19