Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1516 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.7521. Min Act: -0.1700
Data Index: 1000588 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.7521. Min Act: -0.1700
Data Index: 5476620 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.7521. Min Act: -0.1700
Data Index: 7245506 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.5958. Min Act: -0.1700
Data Index: 3125588 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.5333. Min Act: -0.1700
Data Index: 7812011 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.5333. Min Act: -0.1700
Data Index: 8294899 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.5333. Min Act: -0.1700
Data Index: 6459259 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.5021. Min Act: -0.1700
Data Index: 8575227 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.5021. Min Act: -0.1700
Data Index: 6462961 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4708. Min Act: -0.1700
Data Index: 4371201 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4708. Min Act: -0.1700
Data Index: 25412 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4708. Min Act: -0.1700
Data Index: 460994 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4708. Min Act: -0.1700
Data Index: 2227870 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4708. Min Act: -0.1700
Data Index: 53476 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4396. Min Act: -0.1700
Data Index: 5945864 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4708. Min Act: -0.1700
Data Index: 6462962 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4396. Min Act: -0.1700
Data Index: 5603022 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4396. Min Act: -0.1700
Data Index: 4770755 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4396. Min Act: -0.1700
Data Index: 7862190 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7521. Min Range: -4.7521
Max Act: 4.4083. Min Act: -0.1700
Data Index: 4268150 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19