Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1878 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.7782. Min Act: -0.1700
Data Index: 5077914 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.7157. Min Act: -0.1700
Data Index: 334709 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 8611864 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.6532. Min Act: -0.1700
Data Index: 7992252 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5907. Min Act: -0.1700
Data Index: 8607750 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5595. Min Act: -0.1700
Data Index: 2900824 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5595. Min Act: -0.1700
Data Index: 6071192 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5595. Min Act: -0.1700
Data Index: 5468555 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5282. Min Act: -0.1700
Data Index: 3524344 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5282. Min Act: -0.1700
Data Index: 4810922 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.5282. Min Act: -0.1700
Data Index: 5294281 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4970. Min Act: -0.1700
Data Index: 8107740 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4970. Min Act: -0.1700
Data Index: 8382571 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4970. Min Act: -0.1700
Data Index: 5036955 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4657. Min Act: -0.1700
Data Index: 5529605 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4345. Min Act: -0.1700
Data Index: 6944771 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4657. Min Act: -0.1700
Data Index: 3730271 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4345. Min Act: -0.1700
Data Index: 8584221 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4032. Min Act: -0.1700
Data Index: 1212058 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7782. Min Range: -6.7782
Max Act: 6.4032. Min Act: -0.1700
Data Index: 1799432 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19