Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2920 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.3889. Min Act: -0.1700
Data Index: 2957821 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.3264. Min Act: -0.1700
Data Index: 2906204 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.2014. Min Act: -0.1700
Data Index: 1427737 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.0764. Min Act: -0.1700
Data Index: 1955818 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.1077. Min Act: -0.1700
Data Index: 5494218 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.0452. Min Act: -0.1700
Data Index: 3577494 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.0452. Min Act: -0.1700
Data Index: 8672842 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.0139. Min Act: -0.1700
Data Index: 596176 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.0139. Min Act: -0.1700
Data Index: 7119994 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3889. Min Range: -6.3889
Max Act: 6.0139. Min Act: -0.1700
Data Index: 2789619 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9827. Min Act: -0.1700
Data Index: 6927110 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9202. Min Act: -0.1700
Data Index: 553195 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9514. Min Act: -0.1700
Data Index: 909331 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4298776 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9202. Min Act: -0.1700
Data Index: 5093133 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9202. Min Act: -0.1700
Data Index: 583144 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9202. Min Act: -0.1700
Data Index: 3866590 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9202. Min Act: -0.1700
Data Index: 4220174 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9202. Min Act: -0.1700
Data Index: 1127315 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3889. Min Range: -6.3889
Max Act: 5.9202. Min Act: -0.1700
Data Index: 4853267 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19