Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3036 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1776. Min Range: -3.1776
Max Act: 3.1776. Min Act: -0.1700
Data Index: 5486900 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.9726. Min Act: -0.1700
Data Index: 5366807 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.9409. Min Act: -0.1700
Data Index: 1741387 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8934. Min Act: -0.1700
Data Index: 6353037 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8934. Min Act: -0.1700
Data Index: 3803144 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8934. Min Act: -0.1700
Data Index: 4687691 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8934. Min Act: -0.1700
Data Index: 4135614 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8775. Min Act: -0.1700
Data Index: 6666875 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8616. Min Act: -0.1700
Data Index: 3933439 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8457. Min Act: -0.1700
Data Index: 7934773 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8298. Min Act: -0.1700
Data Index: 379465 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8298. Min Act: -0.1700
Data Index: 2452871 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8298. Min Act: -0.1700
Data Index: 7279759 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.8457. Min Act: -0.1700
Data Index: 2723331 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.7980. Min Act: -0.1700
Data Index: 4474410 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.7980. Min Act: -0.1700
Data Index: 7279756 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.7980. Min Act: -0.1700
Data Index: 2952926 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.7980. Min Act: -0.1700
Data Index: 8001239 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.7661. Min Act: -0.1700
Data Index: 2886913 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1776. Min Range: -3.1776
Max Act: 2.7980. Min Act: -0.1700
Data Index: 6113379 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #19