Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 568 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.4140. Min Act: -0.1700
Data Index: 2526002 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.4140. Min Act: -0.1700
Data Index: 72692 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.2890. Min Act: -0.1700
Data Index: 5289183 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.2578. Min Act: -0.1700
Data Index: 3833645 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.2578. Min Act: -0.1700
Data Index: 5131081 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.1640. Min Act: -0.1700
Data Index: 8389041 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.1640. Min Act: -0.1700
Data Index: 735751 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.0703. Min Act: -0.1700
Data Index: 3771863 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4140. Min Range: -7.4140
Max Act: 7.0078. Min Act: -0.1700
Data Index: 4325095 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.9765. Min Act: -0.1700
Data Index: 4265791 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.9453. Min Act: -0.1700
Data Index: 3254403 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.9765. Min Act: -0.1700
Data Index: 7747192 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.9140. Min Act: -0.1700
Data Index: 548500 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.8828. Min Act: -0.1700
Data Index: 672913 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.9140. Min Act: -0.1700
Data Index: 5078349 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.8828. Min Act: -0.1700
Data Index: 5865067 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.8828. Min Act: -0.1700
Data Index: 3089172 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.8828. Min Act: -0.1700
Data Index: 3170469 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.9140. Min Act: -0.1700
Data Index: 2140732 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4140. Min Range: -7.4140
Max Act: 6.8828. Min Act: -0.1700
Data Index: 2112483 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19