Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5942 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.8454. Min Act: -0.1700
Data Index: 4933618 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.6891. Min Act: -0.1700
Data Index: 1512277 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5329. Min Act: -0.1700
Data Index: 5686323 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5016. Min Act: -0.1700
Data Index: 8099881 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.5016. Min Act: -0.1700
Data Index: 6863464 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.4391. Min Act: -0.1700
Data Index: 6571108 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.4704. Min Act: -0.1700
Data Index: 8335524 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5402899 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8383324 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3766. Min Act: -0.1700
Data Index: 1343953 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3454. Min Act: -0.1700
Data Index: 6468564 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3766. Min Act: -0.1700
Data Index: 15756 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3454. Min Act: -0.1700
Data Index: 2273419 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3454. Min Act: -0.1700
Data Index: 7598777 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3454. Min Act: -0.1700
Data Index: 1619383 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.3141. Min Act: -0.1700
Data Index: 3222932 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.2829. Min Act: -0.1700
Data Index: 6193063 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.2829. Min Act: -0.1700
Data Index: 4198563 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.2829. Min Act: -0.1700
Data Index: 5440931 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8454. Min Range: -5.8454
Max Act: 5.2829. Min Act: -0.1700
Data Index: 827276 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19