Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.9895. Min Act: -0.1700
Data Index: 5625523 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.6457. Min Act: -0.1700
Data Index: 3211945 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.5832. Min Act: -0.1700
Data Index: 3124468 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.6145. Min Act: -0.1700
Data Index: 207915 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.5832. Min Act: -0.1700
Data Index: 5057943 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.5832. Min Act: -0.1700
Data Index: 2051451 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.5832. Min Act: -0.1700
Data Index: 6490750 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.5207. Min Act: -0.1700
Data Index: 6753830 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.4895. Min Act: -0.1700
Data Index: 3072041 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.4895. Min Act: -0.1700
Data Index: 7670312 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.4895. Min Act: -0.1700
Data Index: 6750168 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.4582. Min Act: -0.1700
Data Index: 7670313 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.4270. Min Act: -0.1700
Data Index: 8225288 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.4582. Min Act: -0.1700
Data Index: 519470 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.4270. Min Act: -0.1700
Data Index: 6924414 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.3957. Min Act: -0.1700
Data Index: 6355226 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.3957. Min Act: -0.1700
Data Index: 2825144 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.3957. Min Act: -0.1700
Data Index: 4461761 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.3645. Min Act: -0.1700
Data Index: 596607 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9895. Min Range: -5.9895
Max Act: 5.3645. Min Act: -0.1700
Data Index: 713159 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #19