Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3297 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.6762. Min Act: -0.1700
Data Index: 4914572 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.6136. Min Act: -0.1700
Data Index: 1205927 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.6449. Min Act: -0.1700
Data Index: 3477293 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.6449. Min Act: -0.1700
Data Index: 2650574 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.6449. Min Act: -0.1700
Data Index: 2420520 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.6449. Min Act: -0.1700
Data Index: 2133439 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5510. Min Act: -0.1700
Data Index: 222874 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5510. Min Act: -0.1700
Data Index: 1331359 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5510. Min Act: -0.1700
Data Index: 8079377 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5823. Min Act: -0.1700
Data Index: 793739 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5823. Min Act: -0.1700
Data Index: 338573 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5823. Min Act: -0.1700
Data Index: 5246373 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5823. Min Act: -0.1700
Data Index: 2033842 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5823. Min Act: -0.1700
Data Index: 8578719 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5510. Min Act: -0.1700
Data Index: 5979759 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5510. Min Act: -0.1700
Data Index: 7190163 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5823. Min Act: -0.1700
Data Index: 5503179 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5510. Min Act: -0.1700
Data Index: 7454264 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5510. Min Act: -0.1700
Data Index: 4352288 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6762. Min Range: -3.6762
Max Act: 3.5823. Min Act: -0.1700
Data Index: 2682424 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19