Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5072 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.6721. Min Act: -0.1700
Data Index: 2416610 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.5471. Min Act: -0.1700
Data Index: 8233392 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.4846. Min Act: -0.1700
Data Index: 4226341 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.4846. Min Act: -0.1700
Data Index: 4531144 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.4533. Min Act: -0.1700
Data Index: 5015033 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.4221. Min Act: -0.1700
Data Index: 6544486 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.4221. Min Act: -0.1700
Data Index: 4868859 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.3908. Min Act: -0.1700
Data Index: 4874437 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.3596. Min Act: -0.1700
Data Index: 8104418 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.3596. Min Act: -0.1700
Data Index: 617149 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.2658. Min Act: -0.1700
Data Index: 2611846 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.2971. Min Act: -0.1700
Data Index: 8036966 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.2658. Min Act: -0.1700
Data Index: 4906406 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.2658. Min Act: -0.1700
Data Index: 4971536 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.2346. Min Act: -0.1700
Data Index: 3960646 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.2346. Min Act: -0.1700
Data Index: 5365449 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.2033. Min Act: -0.1700
Data Index: 4985169 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.1721. Min Act: -0.1700
Data Index: 5596112 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.1721. Min Act: -0.1700
Data Index: 1405181 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6721. Min Range: -6.6721
Max Act: 6.1721. Min Act: -0.1700
Data Index: 915185 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19