Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1968 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.9630. Min Act: -0.1700
Data Index: 385881 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.7130. Min Act: -0.1700
Data Index: 2127714 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.7130. Min Act: -0.1700
Data Index: 47247 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.6817. Min Act: -0.1700
Data Index: 2388839 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.6505. Min Act: -0.1700
Data Index: 88784 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.6192. Min Act: -0.1700
Data Index: 6160659 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5880. Min Act: -0.1700
Data Index: 811764 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5880. Min Act: -0.1700
Data Index: 8733364 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5880. Min Act: -0.1700
Data Index: 1668319 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5880. Min Act: -0.1700
Data Index: 497415 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.6192. Min Act: -0.1700
Data Index: 6490155 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5567. Min Act: -0.1700
Data Index: 4910724 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5567. Min Act: -0.1700
Data Index: 3362002 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5255. Min Act: -0.1700
Data Index: 4031054 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5255. Min Act: -0.1700
Data Index: 6419909 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5255. Min Act: -0.1700
Data Index: 185109 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5255. Min Act: -0.1700
Data Index: 5549157 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5255. Min Act: -0.1700
Data Index: 7833068 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.5255. Min Act: -0.1700
Data Index: 6679397 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9630. Min Range: -5.9630
Max Act: 5.4942. Min Act: -0.1700
Data Index: 1377368 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19