Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2175 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9847. Min Act: -0.1700
Data Index: 2336493 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9847. Min Act: -0.1693
Data Index: 2336008 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9847. Min Act: -0.1684
Data Index: 1124476 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9530. Min Act: -0.1700
Data Index: 8199576 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9530. Min Act: -0.1700
Data Index: 284603 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9372. Min Act: -0.1700
Data Index: 8401645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1700
Data Index: 879331 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9372. Min Act: -0.1700
Data Index: 3855907 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9372. Min Act: -0.1699
Data Index: 6684493 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9372. Min Act: -0.1686
Data Index: 6684480 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9055. Min Act: -0.1700
Data Index: 775956 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1699
Data Index: 2336010 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1674
Data Index: 6684489 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1700
Data Index: 8157481 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9055. Min Act: -0.1699
Data Index: 711804 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1700
Data Index: 879324 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1700
Data Index: 7593200 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1700
Data Index: 8266472 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1700
Data Index: 4105238 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9847. Min Range: -2.9847
Max Act: 2.9213. Min Act: -0.1700
Data Index: 7385570 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19