Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8547. Min Act: -0.1700
Data Index: 3291669 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8706. Min Act: -0.1700
Data Index: 1213577 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8388. Min Act: -0.1700
Data Index: 6079750 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8388. Min Act: -0.1700
Data Index: 6179818 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 3548507 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 2291933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8229. Min Act: -0.1700
Data Index: 1066778 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 7094512 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 3485765 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8388. Min Act: -0.1700
Data Index: 3319987 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8229. Min Act: -0.1700
Data Index: 4766575 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 7814494 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 2480622 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 565052 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 7150207 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.8070. Min Act: -0.1700
Data Index: 4116857 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7751. Min Act: -0.1700
Data Index: 6744112 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7751. Min Act: -0.1700
Data Index: 5366017 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7751. Min Act: -0.1700
Data Index: 2489494 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8706. Min Range: -2.8706
Max Act: 2.7911. Min Act: -0.1700
Data Index: 5026931 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19