Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2042 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2221. Min Range: -4.2221
Max Act: 4.2221. Min Act: -0.1700
Data Index: 2398697 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2221. Min Range: -4.2221
Max Act: 4.0971. Min Act: -0.1700
Data Index: 6022067 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2221. Min Range: -4.2221
Max Act: 4.0033. Min Act: -0.1700
Data Index: 6049967 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9721. Min Act: -0.1700
Data Index: 7052238 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2221. Min Range: -4.2221
Max Act: 4.0033. Min Act: -0.1700
Data Index: 6895195 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9095. Min Act: -0.1700
Data Index: 8263402 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 1657148 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 327383 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 3947116 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9095. Min Act: -0.1700
Data Index: 1910820 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 8119936 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 4039690 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 7287982 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9721. Min Act: -0.1700
Data Index: 8422030 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 1442458 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9721. Min Act: -0.1700
Data Index: 6509242 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9408. Min Act: -0.1700
Data Index: 510850 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9095. Min Act: -0.1700
Data Index: 2442883 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.9095. Min Act: -0.1700
Data Index: 4247592 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2221. Min Range: -4.2221
Max Act: 3.8783. Min Act: -0.1700
Data Index: 4884154 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19