Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4195 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1757. Min Act: -0.1700
Data Index: 7141471 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1757. Min Act: -0.1700
Data Index: 76940 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1444. Min Act: -0.1700
Data Index: 1444905 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1132. Min Act: -0.1700
Data Index: 8544097 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1132. Min Act: -0.1700
Data Index: 3690577 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.1132. Min Act: -0.1700
Data Index: 1224816 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 6072649 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 6115984 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 8494155 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 3579332 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 3923236 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 2414703 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 6729306 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 2646122 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0819. Min Act: -0.1700
Data Index: 7111743 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0507. Min Act: -0.1700
Data Index: 6997905 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0507. Min Act: -0.1700
Data Index: 4662246 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0507. Min Act: -0.1700
Data Index: 4297094 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0507. Min Act: -0.1700
Data Index: 3821598 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1757. Min Range: -4.1757
Max Act: 4.0507. Min Act: -0.1700
Data Index: 6265706 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19