Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.4318. Min Act: -0.1700
Data Index: 7714551 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.3693. Min Act: -0.1700
Data Index: 1394157 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.2131. Min Act: -0.1700
Data Index: 1084011 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.1818. Min Act: -0.1700
Data Index: 246581 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.1818. Min Act: -0.1700
Data Index: 1587234 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.1193. Min Act: -0.1700
Data Index: 6882862 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.1193. Min Act: -0.1700
Data Index: 5262063 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.0881. Min Act: -0.1700
Data Index: 2238376 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.0568. Min Act: -0.1700
Data Index: 1552323 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.0881. Min Act: -0.1700
Data Index: 4697503 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.0568. Min Act: -0.1700
Data Index: 6772419 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4318. Min Range: -5.4318
Max Act: 5.0568. Min Act: -0.1700
Data Index: 4132467 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9943. Min Act: -0.1700
Data Index: 8387719 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9943. Min Act: -0.1700
Data Index: 4230934 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9943. Min Act: -0.1700
Data Index: 2256724 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9943. Min Act: -0.1700
Data Index: 3551493 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9631. Min Act: -0.1700
Data Index: 4430563 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9631. Min Act: -0.1700
Data Index: 1633712 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9631. Min Act: -0.1700
Data Index: 8645698 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4318. Min Range: -5.4318
Max Act: 4.9318. Min Act: -0.1700
Data Index: 7935893 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19