Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5544 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.7714. Min Act: -0.1700
Data Index: 5194351 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.7089. Min Act: -0.1700
Data Index: 1495547 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.4589. Min Act: -0.1700
Data Index: 8654375 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.3964. Min Act: -0.1700
Data Index: 6270567 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.2714. Min Act: -0.1700
Data Index: 8677593 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.3339. Min Act: -0.1700
Data Index: 411323 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.3339. Min Act: -0.1700
Data Index: 8190390 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.3339. Min Act: -0.1700
Data Index: 6491289 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.2714. Min Act: -0.1700
Data Index: 8082348 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.2089. Min Act: -0.1700
Data Index: 3575375 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.2089. Min Act: -0.1700
Data Index: 5597851 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.2089. Min Act: -0.1700
Data Index: 1168642 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.2089. Min Act: -0.1700
Data Index: 5671317 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.1464. Min Act: -0.1700
Data Index: 8420223 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.1464. Min Act: -0.1700
Data Index: 2308982 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.1464. Min Act: -0.1700
Data Index: 2215506 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.1464. Min Act: -0.1700
Data Index: 2436386 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.2089. Min Act: -0.1700
Data Index: 7189116 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.0839. Min Act: -0.1700
Data Index: 877452 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7714. Min Range: -8.7714
Max Act: 8.0839. Min Act: -0.1700
Data Index: 1819991 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19