Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.7449. Min Act: -0.1700
Data Index: 3707442 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.4012. Min Act: -0.1700
Data Index: 149617 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.3699. Min Act: -0.1700
Data Index: 6965507 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.2762. Min Act: -0.1700
Data Index: 5721875 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.2449. Min Act: -0.1700
Data Index: 2780819 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.2449. Min Act: -0.1700
Data Index: 1232180 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.2137. Min Act: -0.1700
Data Index: 358038 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.2137. Min Act: -0.1700
Data Index: 5446602 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.1824. Min Act: -0.1700
Data Index: 7934063 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.1512. Min Act: -0.1700
Data Index: 2377650 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.1824. Min Act: -0.1700
Data Index: 4976179 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.1512. Min Act: -0.1700
Data Index: 865127 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.1199. Min Act: -0.1700
Data Index: 3861904 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.1199. Min Act: -0.1700
Data Index: 8259259 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 6719195 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 7192750 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 7429788 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 6078961 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.0574. Min Act: -0.1700
Data Index: 874654 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7449. Min Range: -6.7449
Max Act: 6.0262. Min Act: -0.1700
Data Index: 2167284 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19