Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.3658. Min Act: -0.1700
Data Index: 1914291 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.3658. Min Act: -0.1700
Data Index: 7845740 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.3346. Min Act: -0.1700
Data Index: 718931 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.3346. Min Act: -0.1700
Data Index: 7826219 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.2721. Min Act: -0.1700
Data Index: 5739091 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.2721. Min Act: -0.1700
Data Index: 3246202 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.2721. Min Act: -0.1700
Data Index: 1395034 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1783. Min Act: -0.1700
Data Index: 6891174 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1783. Min Act: -0.1700
Data Index: 4422571 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1471. Min Act: -0.1700
Data Index: 3077952 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.2096. Min Act: -0.1700
Data Index: 3530274 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1783. Min Act: -0.1700
Data Index: 3211711 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1783. Min Act: -0.1700
Data Index: 5247142 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1158. Min Act: -0.1700
Data Index: 1828975 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1471. Min Act: -0.1700
Data Index: 5886416 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1783. Min Act: -0.1700
Data Index: 4754094 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1471. Min Act: -0.1700
Data Index: 1879061 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1471. Min Act: -0.1700
Data Index: 6604012 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1471. Min Act: -0.1700
Data Index: 5100622 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3658. Min Range: -6.3658
Max Act: 6.1471. Min Act: -0.1700
Data Index: 8357975 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19