Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.9931. Min Act: -0.1700
Data Index: 4565274 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.8993. Min Act: -0.1700
Data Index: 2166355 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.8524. Min Act: -0.1700
Data Index: 6866434 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.8055. Min Act: -0.1700
Data Index: 1329359 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.8055. Min Act: -0.1700
Data Index: 1490521 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7899. Min Act: -0.1700
Data Index: 6473643 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7899. Min Act: -0.1700
Data Index: 7478640 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7899. Min Act: -0.1700
Data Index: 1170118 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7742. Min Act: -0.1700
Data Index: 3913874 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7899. Min Act: -0.1700
Data Index: 5692372 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7742. Min Act: -0.1700
Data Index: 1055069 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7899. Min Act: -0.1700
Data Index: 6584705 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7742. Min Act: -0.1700
Data Index: 5947429 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7742. Min Act: -0.1700
Data Index: 4667909 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7742. Min Act: -0.1700
Data Index: 752257 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7742. Min Act: -0.1700
Data Index: 6473642 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7429. Min Act: -0.1700
Data Index: 2861398 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7117. Min Act: -0.1700
Data Index: 4200955 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7429. Min Act: -0.1700
Data Index: 4730753 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9931. Min Range: -3.9931
Max Act: 3.7429. Min Act: -0.1700
Data Index: 1078597 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19