Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3197 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1125. Min Range: -6.1125
Max Act: 6.1125. Min Act: -0.1700
Data Index: 6434050 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.8938. Min Act: -0.1700
Data Index: 4582596 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.9563. Min Act: -0.1700
Data Index: 4537862 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.7688. Min Act: -0.1700
Data Index: 8669590 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.7063. Min Act: -0.1700
Data Index: 5967998 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.7063. Min Act: -0.1700
Data Index: 3257620 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.6750. Min Act: -0.1700
Data Index: 7804615 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.7063. Min Act: -0.1700
Data Index: 1336523 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.6438. Min Act: -0.1700
Data Index: 2516218 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.6438. Min Act: -0.1700
Data Index: 5827003 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.6125. Min Act: -0.1700
Data Index: 6895465 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.6125. Min Act: -0.1700
Data Index: 3831447 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.5813. Min Act: -0.1700
Data Index: 6584349 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.6125. Min Act: -0.1700
Data Index: 3670914 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.6125. Min Act: -0.1700
Data Index: 3110183 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.5500. Min Act: -0.1700
Data Index: 3352269 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.5813. Min Act: -0.1700
Data Index: 7760702 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.5813. Min Act: -0.1700
Data Index: 4154431 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.5813. Min Act: -0.1700
Data Index: 6480754 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1125. Min Range: -6.1125
Max Act: 5.5813. Min Act: -0.1700
Data Index: 5290235 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19