Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1414 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.5190. Min Act: -0.1700
Data Index: 7031637 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.3002. Min Act: -0.1700
Data Index: 4107867 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.3002. Min Act: -0.1700
Data Index: 1512467 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.2377. Min Act: -0.1700
Data Index: 8829724 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.2377. Min Act: -0.1700
Data Index: 6949580 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.2065. Min Act: -0.1700
Data Index: 1485189 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.2065. Min Act: -0.1700
Data Index: 5381292 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.2065. Min Act: -0.1700
Data Index: 8829725 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1752. Min Act: -0.1700
Data Index: 6949585 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.2065. Min Act: -0.1700
Data Index: 3941919 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1440. Min Act: -0.1700
Data Index: 339413 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1127. Min Act: -0.1700
Data Index: 4834578 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1440. Min Act: -0.1700
Data Index: 121732 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1440. Min Act: -0.1700
Data Index: 5521611 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.0815. Min Act: -0.1700
Data Index: 4481641 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1127. Min Act: -0.1700
Data Index: 8026211 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1127. Min Act: -0.1700
Data Index: 4629988 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.1127. Min Act: -0.1700
Data Index: 2145073 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.0815. Min Act: -0.1700
Data Index: 5564443 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5190. Min Range: -8.5190
Max Act: 8.0815. Min Act: -0.1700
Data Index: 8290044 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19