Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0101. Min Range: -6.0101
Max Act: 6.0101. Min Act: -0.1700
Data Index: 4667912 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.9163. Min Act: -0.1700
Data Index: 4657241 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.8851. Min Act: -0.1700
Data Index: 4667911 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.8538. Min Act: -0.1700
Data Index: 4156015 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.7913. Min Act: -0.1700
Data Index: 2477275 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.7913. Min Act: -0.1700
Data Index: 918954 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.7913. Min Act: -0.1700
Data Index: 4442756 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.7913. Min Act: -0.1700
Data Index: 6756058 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.7288. Min Act: -0.1700
Data Index: 4421568 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6976. Min Act: -0.1700
Data Index: 7816001 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6663. Min Act: -0.1700
Data Index: 8160346 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6976. Min Act: -0.1700
Data Index: 2548971 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6976. Min Act: -0.1700
Data Index: 2649855 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6351. Min Act: -0.1700
Data Index: 4481718 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6663. Min Act: -0.1700
Data Index: 3903082 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6663. Min Act: -0.1700
Data Index: 4872779 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6663. Min Act: -0.1700
Data Index: 330080 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6038. Min Act: -0.1700
Data Index: 6487227 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6351. Min Act: -0.1700
Data Index: 6202259 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0101. Min Range: -6.0101
Max Act: 5.6663. Min Act: -0.1700
Data Index: 3960834 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19