Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4467. Min Range: -4.4467
Max Act: 4.4467. Min Act: -0.1700
Data Index: 1911487 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4467. Min Range: -4.4467
Max Act: 4.3217. Min Act: -0.1700
Data Index: 710014 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4467. Min Range: -4.4467
Max Act: 4.0404. Min Act: -0.1700
Data Index: 982549 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4467. Min Range: -4.4467
Max Act: 4.0404. Min Act: -0.1700
Data Index: 5011846 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4467. Min Range: -4.4467
Max Act: 4.0404. Min Act: -0.1700
Data Index: 5948348 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4467. Min Range: -4.4467
Max Act: 4.0092. Min Act: -0.1700
Data Index: 6937619 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9467. Min Act: -0.1700
Data Index: 870741 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9467. Min Act: -0.1700
Data Index: 1261130 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9154. Min Act: -0.1700
Data Index: 7647167 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9154. Min Act: -0.1700
Data Index: 4775217 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9154. Min Act: -0.1700
Data Index: 4378244 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9154. Min Act: -0.1700
Data Index: 2894655 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.8841. Min Act: -0.1700
Data Index: 8294149 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9154. Min Act: -0.1700
Data Index: 7027987 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.9154. Min Act: -0.1700
Data Index: 1566711 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.8529. Min Act: -0.1700
Data Index: 8296979 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.8841. Min Act: -0.1700
Data Index: 87830 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.8529. Min Act: -0.1700
Data Index: 4590555 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.8841. Min Act: -0.1700
Data Index: 7702583 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4467. Min Range: -4.4467
Max Act: 3.8529. Min Act: -0.1700
Data Index: 4018478 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19