Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6358 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.7709. Min Act: -0.1700
Data Index: 2780272 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.6459. Min Act: -0.1700
Data Index: 7532 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.5209. Min Act: -0.1700
Data Index: 6183859 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.4271. Min Act: -0.1700
Data Index: 5764355 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.4584. Min Act: -0.1700
Data Index: 5547412 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.4271. Min Act: -0.1700
Data Index: 1339319 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.3959. Min Act: -0.1700
Data Index: 6941727 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.3646. Min Act: -0.1700
Data Index: 493632 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.3646. Min Act: -0.1700
Data Index: 1415600 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.3021. Min Act: -0.1700
Data Index: 1296085 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3374304 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 4573041 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3784363 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.2396. Min Act: -0.1700
Data Index: 2841168 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.1771. Min Act: -0.1700
Data Index: 4253383 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.2084. Min Act: -0.1700
Data Index: 6236621 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.2084. Min Act: -0.1700
Data Index: 863205 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6633950 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.1771. Min Act: -0.1700
Data Index: 658600 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7709. Min Range: -6.7709
Max Act: 6.1771. Min Act: -0.1700
Data Index: 294285 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19