Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1225 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.6668. Min Act: -0.1700
Data Index: 7152048 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.6042. Min Act: -0.1700
Data Index: 1357306 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.6355. Min Act: -0.1700
Data Index: 2235870 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.5729. Min Act: -0.1700
Data Index: 3439735 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.5103. Min Act: -0.1700
Data Index: 7933206 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4946. Min Act: -0.1700
Data Index: 7634419 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4790. Min Act: -0.1700
Data Index: 5816006 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4946. Min Act: -0.1700
Data Index: 7676438 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4790. Min Act: -0.1700
Data Index: 2711263 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4790. Min Act: -0.1700
Data Index: 5808984 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4476. Min Act: -0.1700
Data Index: 6034607 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4633. Min Act: -0.1700
Data Index: 4073988 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4320. Min Act: -0.1700
Data Index: 2551680 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4320. Min Act: -0.1700
Data Index: 1357307 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4633. Min Act: -0.1700
Data Index: 6034603 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4633. Min Act: -0.1700
Data Index: 3439736 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4633. Min Act: -0.1700
Data Index: 51399 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4320. Min Act: -0.1700
Data Index: 6822072 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4320. Min Act: -0.1700
Data Index: 3439737 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6668. Min Range: -3.6668
Max Act: 3.4320. Min Act: -0.1700
Data Index: 1370805 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19