Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1478 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.8768. Min Act: -0.1700
Data Index: 8183154 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.5952. Min Act: -0.1700
Data Index: 3652911 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4699. Min Act: -0.1700
Data Index: 3029264 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.5013. Min Act: -0.1700
Data Index: 3672979 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.5326. Min Act: -0.1700
Data Index: 3731623 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4699. Min Act: -0.1700
Data Index: 8661776 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4386. Min Act: -0.1700
Data Index: 920051 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4543. Min Act: -0.1700
Data Index: 596501 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4543. Min Act: -0.1700
Data Index: 7393378 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4543. Min Act: -0.1700
Data Index: 1362453 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4229. Min Act: -0.1700
Data Index: 650710 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.3759. Min Act: -0.1700
Data Index: 3056059 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.3445. Min Act: -0.1700
Data Index: 1188959 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4856. Min Act: -0.1700
Data Index: 1859686 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4386. Min Act: -0.1700
Data Index: 1223909 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4072. Min Act: -0.1700
Data Index: 4783014 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4229. Min Act: -0.1700
Data Index: 4460253 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.4229. Min Act: -0.1700
Data Index: 4223403 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.3602. Min Act: -0.1700
Data Index: 3430082 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8768. Min Range: -3.8768
Max Act: 3.3131. Min Act: -0.1700
Data Index: 608388 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19