Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2837 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.3300. Min Act: -0.1700
Data Index: 4377377 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.3300. Min Act: -0.1700
Data Index: 6880711 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.2675. Min Act: -0.1700
Data Index: 6433317 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.2362. Min Act: -0.1700
Data Index: 8635097 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.2362. Min Act: -0.1700
Data Index: 62528 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.2050. Min Act: -0.1700
Data Index: 5897143 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1737. Min Act: -0.1700
Data Index: 1922232 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1737. Min Act: -0.1700
Data Index: 5500325 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1737. Min Act: -0.1700
Data Index: 667817 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1737. Min Act: -0.1700
Data Index: 916615 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1425. Min Act: -0.1700
Data Index: 7745332 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1425. Min Act: -0.1700
Data Index: 7998720 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1737. Min Act: -0.1700
Data Index: 1459801 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1737. Min Act: -0.1700
Data Index: 585413 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1425. Min Act: -0.1700
Data Index: 1734083 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1112. Min Act: -0.1700
Data Index: 3705654 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.0800. Min Act: -0.1700
Data Index: 4447674 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.1112. Min Act: -0.1700
Data Index: 657112 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.0800. Min Act: -0.1700
Data Index: 5459691 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3300. Min Range: -5.3300
Max Act: 5.0800. Min Act: -0.1700
Data Index: 6154208 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19