Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.7578. Min Act: -0.1700
Data Index: 4575839 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.7578. Min Act: -0.1700
Data Index: 1202277 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.6328. Min Act: -0.1700
Data Index: 5347046 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.6016. Min Act: -0.1700
Data Index: 4640386 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5703. Min Act: -0.1700
Data Index: 4543845 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5391. Min Act: -0.1700
Data Index: 1492891 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5391. Min Act: -0.1700
Data Index: 5781828 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5078. Min Act: -0.1700
Data Index: 308559 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5078. Min Act: -0.1700
Data Index: 180008 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5078. Min Act: -0.1700
Data Index: 4519952 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4766. Min Act: -0.1700
Data Index: 6035504 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4766. Min Act: -0.1700
Data Index: 4990937 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4766. Min Act: -0.1700
Data Index: 6732800 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4766. Min Act: -0.1700
Data Index: 3402628 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4766. Min Act: -0.1700
Data Index: 2180574 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4453. Min Act: -0.1700
Data Index: 7782526 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4453. Min Act: -0.1700
Data Index: 8386941 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4453. Min Act: -0.1700
Data Index: 5935683 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4141. Min Act: -0.1700
Data Index: 1569710 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4141. Min Act: -0.1700
Data Index: 1625900 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19