Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.6381. Min Act: -0.1700
Data Index: 6812947 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.5253. Min Act: -0.1700
Data Index: 5731328 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.5091. Min Act: -0.1700
Data Index: 8279651 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.5091. Min Act: -0.1700
Data Index: 2658082 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4767. Min Act: -0.1700
Data Index: 7181020 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4442. Min Act: -0.1700
Data Index: 2689847 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4604. Min Act: -0.1700
Data Index: 4077024 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4442. Min Act: -0.1700
Data Index: 3191309 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4116. Min Act: -0.1700
Data Index: 6749425 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3953. Min Act: -0.1700
Data Index: 186844 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4116. Min Act: -0.1700
Data Index: 695275 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4116. Min Act: -0.1700
Data Index: 579701 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3790. Min Act: -0.1700
Data Index: 7298210 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.4116. Min Act: -0.1700
Data Index: 5414918 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3790. Min Act: -0.1700
Data Index: 3162138 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3626. Min Act: -0.1700
Data Index: 3618932 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3626. Min Act: -0.1700
Data Index: 1058604 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3626. Min Act: -0.1700
Data Index: 5388513 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3298. Min Act: -0.1700
Data Index: 6494214 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6381. Min Range: -2.6381
Max Act: 2.3462. Min Act: -0.1700
Data Index: 5242801 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19