Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 981 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.9127. Min Act: -0.1700
Data Index: 2400200 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.7252. Min Act: -0.1700
Data Index: 5807850 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.6939. Min Act: -0.1700
Data Index: 3580510 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.6939. Min Act: -0.1700
Data Index: 2749927 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.5064. Min Act: -0.1700
Data Index: 1181136 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.5377. Min Act: -0.1700
Data Index: 1727117 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.5377. Min Act: -0.1700
Data Index: 6987234 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.5689. Min Act: -0.1700
Data Index: 717752 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.5064. Min Act: -0.1700
Data Index: 7387317 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.4127. Min Act: -0.1700
Data Index: 932543 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.3814. Min Act: -0.1700
Data Index: 4278478 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.4439. Min Act: -0.1700
Data Index: 4009773 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.4127. Min Act: -0.1700
Data Index: 7115922 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.4127. Min Act: -0.1700
Data Index: 7836699 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.3814. Min Act: -0.1700
Data Index: 7811137 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.3814. Min Act: -0.1700
Data Index: 3728174 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.3189. Min Act: -0.1700
Data Index: 3982139 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.3502. Min Act: -0.1700
Data Index: 7294056 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.3502. Min Act: -0.1700
Data Index: 4591018 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9127. Min Range: -5.9127
Max Act: 5.2564. Min Act: -0.1700
Data Index: 2928052 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19