Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.1787. Min Act: -0.1700
Data Index: 5442938 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.1120. Min Act: -0.1700
Data Index: 8445802 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0953. Min Act: -0.1700
Data Index: 6415341 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0449. Min Act: -0.1700
Data Index: 1240145 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0449. Min Act: -0.1700
Data Index: 7756386 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0449. Min Act: -0.1700
Data Index: 3198928 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0449. Min Act: -0.1700
Data Index: 3198929 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0280. Min Act: -0.1700
Data Index: 2062238 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0449. Min Act: -0.1700
Data Index: 6869161 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0449. Min Act: -0.1700
Data Index: 86229 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0449. Min Act: -0.1700
Data Index: 1651867 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0112. Min Act: -0.1700
Data Index: 3668728 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0112. Min Act: -0.1700
Data Index: 8785243 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0112. Min Act: -0.1700
Data Index: 6069027 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1787. Min Range: -2.1787
Max Act: 1.9943. Min Act: -0.1700
Data Index: 4646258 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0112. Min Act: -0.1700
Data Index: 5793727 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1787. Min Range: -2.1787
Max Act: 2.0112. Min Act: -0.1700
Data Index: 8591205 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1787. Min Range: -2.1787
Max Act: 1.9943. Min Act: -0.1700
Data Index: 6609813 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1787. Min Range: -2.1787
Max Act: 1.9943. Min Act: -0.1700
Data Index: 48677 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1787. Min Range: -2.1787
Max Act: 1.9943. Min Act: -0.1700
Data Index: 4433594 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19