Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.7052. Min Act: -0.1700
Data Index: 8112231 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.5802. Min Act: -0.1700
Data Index: 1936593 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.5177. Min Act: -0.1700
Data Index: 6732094 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.4552. Min Act: -0.1700
Data Index: 2622361 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.3614. Min Act: -0.1700
Data Index: 8112229 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.3614. Min Act: -0.1700
Data Index: 7972767 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2989. Min Act: -0.1700
Data Index: 8824685 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2989. Min Act: -0.1700
Data Index: 4085870 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2677. Min Act: -0.1700
Data Index: 7179783 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2364. Min Act: -0.1700
Data Index: 7276768 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2364. Min Act: -0.1700
Data Index: 8377923 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2364. Min Act: -0.1700
Data Index: 5648811 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2052. Min Act: -0.1700
Data Index: 8027649 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2052. Min Act: -0.1700
Data Index: 8739035 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2052. Min Act: -0.1700
Data Index: 357270 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2052. Min Act: -0.1700
Data Index: 1207 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2052. Min Act: -0.1700
Data Index: 2730011 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.1739. Min Act: -0.1700
Data Index: 863255 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.1739. Min Act: -0.1700
Data Index: 4535112 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7052. Min Range: -5.7052
Max Act: 5.2052. Min Act: -0.1700
Data Index: 6939568 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19