Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 825 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.2527. Min Act: -0.1700
Data Index: 6496373 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.1590. Min Act: -0.1700
Data Index: 3667433 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.1590. Min Act: -0.1700
Data Index: 5494625 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0965. Min Act: -0.1700
Data Index: 2048592 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.1277. Min Act: -0.1700
Data Index: 5321435 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0652. Min Act: -0.1700
Data Index: 2314246 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0965. Min Act: -0.1700
Data Index: 5887558 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0652. Min Act: -0.1700
Data Index: 5670681 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0339. Min Act: -0.1700
Data Index: 4265367 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0027. Min Act: -0.1700
Data Index: 1951064 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2527. Min Range: -4.2527
Max Act: 4.0027. Min Act: -0.1700
Data Index: 4060923 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9714. Min Act: -0.1700
Data Index: 5716927 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9714. Min Act: -0.1700
Data Index: 7185163 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9714. Min Act: -0.1700
Data Index: 78572 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9402. Min Act: -0.1700
Data Index: 8230832 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9402. Min Act: -0.1700
Data Index: 3979644 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.8776. Min Act: -0.1700
Data Index: 4293887 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9089. Min Act: -0.1700
Data Index: 1030842 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9402. Min Act: -0.1700
Data Index: 5459282 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2527. Min Range: -4.2527
Max Act: 3.9089. Min Act: -0.1700
Data Index: 2485007 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19