Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2695. Min Range: -8.2695
Max Act: 8.2695. Min Act: -0.1700
Data Index: 6537134 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2695. Min Range: -8.2695
Max Act: 8.1445. Min Act: -0.1700
Data Index: 1671787 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2695. Min Range: -8.2695
Max Act: 8.0820. Min Act: -0.1700
Data Index: 1112236 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2695. Min Range: -8.2695
Max Act: 8.0820. Min Act: -0.1700
Data Index: 3360160 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2695. Min Range: -8.2695
Max Act: 8.0820. Min Act: -0.1700
Data Index: 5066652 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2695. Min Range: -8.2695
Max Act: 8.0195. Min Act: -0.1700
Data Index: 2162211 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.9570. Min Act: -0.1700
Data Index: 7466618 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.9570. Min Act: -0.1700
Data Index: 6609144 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.9570. Min Act: -0.1700
Data Index: 6243704 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.8945. Min Act: -0.1700
Data Index: 3159831 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.8633. Min Act: -0.1700
Data Index: 5965346 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.8633. Min Act: -0.1700
Data Index: 3845554 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.8008. Min Act: -0.1700
Data Index: 3998849 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.8008. Min Act: -0.1700
Data Index: 4304085 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.8008. Min Act: -0.1700
Data Index: 519982 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.8008. Min Act: -0.1700
Data Index: 4196752 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.7383. Min Act: -0.1700
Data Index: 8059775 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.7070. Min Act: -0.1700
Data Index: 5615101 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.6758. Min Act: -0.1700
Data Index: 4487370 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2695. Min Range: -8.2695
Max Act: 7.7070. Min Act: -0.1700
Data Index: 4193282 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19