Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2820 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.5706. Min Act: -0.1700
Data Index: 3396643 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.5394. Min Act: -0.1700
Data Index: 1675209 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.4456. Min Act: -0.1700
Data Index: 6517919 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.4769. Min Act: -0.1700
Data Index: 7023574 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.4144. Min Act: -0.1700
Data Index: 8110971 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.3519. Min Act: -0.1700
Data Index: 3278520 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.3831. Min Act: -0.1700
Data Index: 8154688 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.3206. Min Act: -0.1700
Data Index: 7508095 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.3519. Min Act: -0.1700
Data Index: 110987 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2893. Min Act: -0.1700
Data Index: 7653773 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2893. Min Act: -0.1700
Data Index: 6115177 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2581. Min Act: -0.1700
Data Index: 2576824 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.3206. Min Act: -0.1700
Data Index: 7801853 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2581. Min Act: -0.1700
Data Index: 5314602 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2581. Min Act: -0.1700
Data Index: 4436482 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2581. Min Act: -0.1700
Data Index: 7700815 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2581. Min Act: -0.1700
Data Index: 190868 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2581. Min Act: -0.1700
Data Index: 2307638 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.2268. Min Act: -0.1700
Data Index: 8506432 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5706. Min Range: -4.5706
Max Act: 4.1643. Min Act: -0.1700
Data Index: 778755 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19