Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5118 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1711. Min Range: -7.1711
Max Act: 7.1711. Min Act: -0.1700
Data Index: 4882547 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1711. Min Range: -7.1711
Max Act: 7.1398. Min Act: -0.1700
Data Index: 6094844 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1711. Min Range: -7.1711
Max Act: 7.1398. Min Act: -0.1700
Data Index: 7706647 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.9836. Min Act: -0.1700
Data Index: 8041550 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.9211. Min Act: -0.1700
Data Index: 5934106 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.9211. Min Act: -0.1700
Data Index: 4396552 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.9211. Min Act: -0.1700
Data Index: 1192005 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.8273. Min Act: -0.1700
Data Index: 4945500 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.8586. Min Act: -0.1700
Data Index: 4747811 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.8586. Min Act: -0.1700
Data Index: 1900905 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.8273. Min Act: -0.1700
Data Index: 3042610 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.8273. Min Act: -0.1700
Data Index: 7404785 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.8273. Min Act: -0.1700
Data Index: 928605 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.8273. Min Act: -0.1700
Data Index: 3994543 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.7961. Min Act: -0.1700
Data Index: 4347839 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.7648. Min Act: -0.1700
Data Index: 3257833 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.7023. Min Act: -0.1700
Data Index: 6686260 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.7023. Min Act: -0.1700
Data Index: 5605525 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.7023. Min Act: -0.1700
Data Index: 4918807 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1711. Min Range: -7.1711
Max Act: 6.7023. Min Act: -0.1700
Data Index: 2503104 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19