Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.3389. Min Act: -0.1700
Data Index: 1419169 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.3389. Min Act: -0.1700
Data Index: 6836237 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.2764. Min Act: -0.1700
Data Index: 2695900 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.2452. Min Act: -0.1700
Data Index: 3813770 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.2139. Min Act: -0.1700
Data Index: 4146177 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1827. Min Act: -0.1700
Data Index: 2395784 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1514. Min Act: -0.1700
Data Index: 1919007 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1827. Min Act: -0.1700
Data Index: 1166950 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1514. Min Act: -0.1700
Data Index: 2964844 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1202. Min Act: -0.1700
Data Index: 1438532 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1827. Min Act: -0.1700
Data Index: 5590914 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1292977 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.1202. Min Act: -0.1700
Data Index: 2075044 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 8238874 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 5681024 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0577. Min Act: -0.1700
Data Index: 6835220 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1133907 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0577. Min Act: -0.1700
Data Index: 898901 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0577. Min Act: -0.1700
Data Index: 4434608 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3389. Min Range: -5.3389
Max Act: 5.0889. Min Act: -0.1700
Data Index: 4984304 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19