Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4555 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.5140. Min Act: -0.1700
Data Index: 980653 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.3577. Min Act: -0.1700
Data Index: 980652 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.2015. Min Act: -0.1700
Data Index: 2630757 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1702. Min Act: -0.1700
Data Index: 6666145 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1702. Min Act: -0.1700
Data Index: 2630758 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1390. Min Act: -0.1698
Data Index: 980651 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1390. Min Act: -0.1700
Data Index: 4891975 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1077. Min Act: -0.1700
Data Index: 980650 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.1077. Min Act: -0.1700
Data Index: 980656 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4671132 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0140. Min Act: -0.1700
Data Index: 980655 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0140. Min Act: -0.1700
Data Index: 980654 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5140. Min Range: -5.5140
Max Act: 5.0452. Min Act: -0.1700
Data Index: 1458226 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5140. Min Range: -5.5140
Max Act: 4.9827. Min Act: -0.1700
Data Index: 4891970 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5140. Min Range: -5.5140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 2630759 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5140. Min Range: -5.5140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 1955122 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5140. Min Range: -5.5140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 1955124 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5140. Min Range: -5.5140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 6666150 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5140. Min Range: -5.5140
Max Act: 4.9515. Min Act: -0.1700
Data Index: 8627675 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5140. Min Range: -5.5140
Max Act: 4.9202. Min Act: -0.1700
Data Index: 232747 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19