Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1773 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.6039. Min Act: -0.1700
Data Index: 4006300 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.5726. Min Act: -0.1700
Data Index: 4306487 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.5101. Min Act: -0.1700
Data Index: 8158886 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.4164. Min Act: -0.1700
Data Index: 5387362 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.3851. Min Act: -0.1700
Data Index: 2088224 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.3539. Min Act: -0.1700
Data Index: 91046 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.3226. Min Act: -0.1700
Data Index: 4180990 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.3226. Min Act: -0.1700
Data Index: 1787914 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.2914. Min Act: -0.1700
Data Index: 6260812 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.2601. Min Act: -0.1700
Data Index: 5321366 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.2601. Min Act: -0.1700
Data Index: 6895656 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.2914. Min Act: -0.1700
Data Index: 3434362 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.1976. Min Act: -0.1700
Data Index: 6636772 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.1664. Min Act: -0.1700
Data Index: 7558018 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.1664. Min Act: -0.1700
Data Index: 8686009 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.1351. Min Act: -0.1700
Data Index: 6938613 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.1039. Min Act: -0.1700
Data Index: 7607411 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.0101. Min Act: -0.1700
Data Index: 7954991 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.0101. Min Act: -0.1700
Data Index: 7915215 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6039. Min Range: -5.6039
Max Act: 5.0101. Min Act: -0.1700
Data Index: 2186646 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19