Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2356. Min Range: -5.2356
Max Act: 5.2356. Min Act: -0.1700
Data Index: 8828656 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2356. Min Range: -5.2356
Max Act: 5.1731. Min Act: -0.1700
Data Index: 461391 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2356. Min Range: -5.2356
Max Act: 5.0793. Min Act: -0.1700
Data Index: 8776284 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2356. Min Range: -5.2356
Max Act: 5.0168. Min Act: -0.1700
Data Index: 7314434 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.7356. Min Act: -0.1700
Data Index: 3215120 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.7043. Min Act: -0.1700
Data Index: 1323979 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.7668. Min Act: -0.1700
Data Index: 1165448 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.7043. Min Act: -0.1700
Data Index: 5083103 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.7043. Min Act: -0.1700
Data Index: 5659231 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.7043. Min Act: -0.1700
Data Index: 8289619 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.7043. Min Act: -0.1700
Data Index: 1553914 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6731. Min Act: -0.1700
Data Index: 969580 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6731. Min Act: -0.1700
Data Index: 4203353 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6731. Min Act: -0.1700
Data Index: 775334 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6731. Min Act: -0.1700
Data Index: 4627922 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6731. Min Act: -0.1700
Data Index: 1895515 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6418. Min Act: -0.1700
Data Index: 272693 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6418. Min Act: -0.1700
Data Index: 36055 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6418. Min Act: -0.1700
Data Index: 4396129 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2356. Min Range: -5.2356
Max Act: 4.6106. Min Act: -0.1700
Data Index: 5587662 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19