Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5776 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0857. Min Range: -5.0857
Max Act: 5.0857. Min Act: -0.1700
Data Index: 1681897 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0857. Min Range: -5.0857
Max Act: 5.0232. Min Act: -0.1700
Data Index: 670039 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.9607. Min Act: -0.1700
Data Index: 6702829 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.8982. Min Act: -0.1700
Data Index: 3688094 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.8669. Min Act: -0.1700
Data Index: 7437468 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7732. Min Act: -0.1700
Data Index: 2966739 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 4312492 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 5519593 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 2666026 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 7240756 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 3742477 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 1683259 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 428199 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7419. Min Act: -0.1700
Data Index: 4451986 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7107. Min Act: -0.1700
Data Index: 2470537 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7107. Min Act: -0.1700
Data Index: 1309840 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.6794. Min Act: -0.1700
Data Index: 3144749 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.7107. Min Act: -0.1700
Data Index: 50275 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.6794. Min Act: -0.1700
Data Index: 4703701 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0857. Min Range: -5.0857
Max Act: 4.6794. Min Act: -0.1700
Data Index: 8381060 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19