Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2567. Min Range: -5.2567
Max Act: 5.2567. Min Act: -0.1700
Data Index: 4796122 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.7567. Min Act: -0.1700
Data Index: 944451 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.7567. Min Act: -0.1700
Data Index: 8524176 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.7254. Min Act: -0.1700
Data Index: 4098316 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.6942. Min Act: -0.1700
Data Index: 4749584 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.7254. Min Act: -0.1700
Data Index: 735632 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.6629. Min Act: -0.1700
Data Index: 2162230 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.6629. Min Act: -0.1700
Data Index: 7826538 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.6317. Min Act: -0.1700
Data Index: 1378508 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.6629. Min Act: -0.1700
Data Index: 5910574 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 3595262 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.6004. Min Act: -0.1700
Data Index: 1002306 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 2422236 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.6004. Min Act: -0.1700
Data Index: 4894949 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5379. Min Act: -0.1700
Data Index: 3669822 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 7918809 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 5413121 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 3037467 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5067. Min Act: -0.1700
Data Index: 4920364 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2567. Min Range: -5.2567
Max Act: 4.5692. Min Act: -0.1700
Data Index: 7254103 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19