Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2574. Min Range: -7.2574
Max Act: 7.2574. Min Act: -0.1700
Data Index: 5424466 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.9762. Min Act: -0.1700
Data Index: 4366654 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.9137. Min Act: -0.1700
Data Index: 1975880 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.8512. Min Act: -0.1700
Data Index: 5738054 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.8512. Min Act: -0.1700
Data Index: 184059 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.8199. Min Act: -0.1700
Data Index: 7144408 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.6949. Min Act: -0.1700
Data Index: 6446493 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.6637. Min Act: -0.1700
Data Index: 1009191 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.6949. Min Act: -0.1700
Data Index: 6728989 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.6637. Min Act: -0.1700
Data Index: 7540589 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.6012. Min Act: -0.1700
Data Index: 5233663 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.6012. Min Act: -0.1700
Data Index: 6728991 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.5387. Min Act: -0.1700
Data Index: 2702776 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.5387. Min Act: -0.1700
Data Index: 1159460 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.5074. Min Act: -0.1700
Data Index: 6928842 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.4762. Min Act: -0.1700
Data Index: 2806286 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.5074. Min Act: -0.1700
Data Index: 5742050 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.5387. Min Act: -0.1700
Data Index: 3742267 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.5074. Min Act: -0.1700
Data Index: 7117089 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2574. Min Range: -7.2574
Max Act: 6.4762. Min Act: -0.1700
Data Index: 6764036 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19