Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2039 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.9534. Min Act: -0.1700
Data Index: 2253858 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.8283. Min Act: -0.1700
Data Index: 5343033 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.8596. Min Act: -0.1700
Data Index: 6015624 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.8283. Min Act: -0.1700
Data Index: 7755533 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.8283. Min Act: -0.1700
Data Index: 1422008 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7970. Min Act: -0.1700
Data Index: 1293570 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.8283. Min Act: -0.1700
Data Index: 2636850 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7970. Min Act: -0.1700
Data Index: 6981857 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7657. Min Act: -0.1700
Data Index: 5049496 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7345. Min Act: -0.1700
Data Index: 7141308 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7032. Min Act: -0.1700
Data Index: 1234037 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.6719. Min Act: -0.1700
Data Index: 6140490 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7345. Min Act: -0.1700
Data Index: 819744 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7032. Min Act: -0.1700
Data Index: 7706869 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7032. Min Act: -0.1700
Data Index: 5313252 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.7032. Min Act: -0.1700
Data Index: 7317735 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.6719. Min Act: -0.1700
Data Index: 1944818 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.6719. Min Act: -0.1700
Data Index: 7455666 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.6406. Min Act: -0.1700
Data Index: 1383666 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9534. Min Range: -3.9534
Max Act: 3.6719. Min Act: -0.1700
Data Index: 4505603 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19