Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1131. Min Range: -4.1131
Max Act: 4.1131. Min Act: -0.1700
Data Index: 1336361 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.9880. Min Act: -0.1700
Data Index: 3572843 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.9255. Min Act: -0.1700
Data Index: 4605995 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8942. Min Act: -0.1700
Data Index: 8293801 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.9255. Min Act: -0.1700
Data Index: 3295721 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8630. Min Act: -0.1700
Data Index: 3707874 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8317. Min Act: -0.1700
Data Index: 3561160 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8317. Min Act: -0.1700
Data Index: 4824463 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8317. Min Act: -0.1700
Data Index: 8367666 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8004. Min Act: -0.1700
Data Index: 5314664 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8004. Min Act: -0.1700
Data Index: 3657256 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8004. Min Act: -0.1700
Data Index: 560742 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.8004. Min Act: -0.1700
Data Index: 2092496 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.7691. Min Act: -0.1700
Data Index: 5074485 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.7691. Min Act: -0.1700
Data Index: 361106 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.7379. Min Act: -0.1700
Data Index: 6195628 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.7379. Min Act: -0.1700
Data Index: 6147352 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.7379. Min Act: -0.1700
Data Index: 1510221 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.7379. Min Act: -0.1700
Data Index: 6849444 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1131. Min Range: -4.1131
Max Act: 3.7379. Min Act: -0.1700
Data Index: 2280451 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19