Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.3715. Min Act: -0.1700
Data Index: 4315232 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.2465. Min Act: -0.1700
Data Index: 3505715 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.2465. Min Act: -0.1700
Data Index: 7919811 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.2465. Min Act: -0.1700
Data Index: 2889000 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.2465. Min Act: -0.1700
Data Index: 7868727 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.2465. Min Act: -0.1700
Data Index: 6489019 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.2465. Min Act: -0.1700
Data Index: 4885656 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.1840. Min Act: -0.1700
Data Index: 7218831 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.1840. Min Act: -0.1700
Data Index: 6536309 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.0590. Min Act: -0.1700
Data Index: 4504834 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.3715. Min Range: -11.3715
Max Act: 11.0590. Min Act: -0.1700
Data Index: 3189138 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.9965. Min Act: -0.1700
Data Index: 165327 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.9340. Min Act: -0.1700
Data Index: 6266001 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.9340. Min Act: -0.1700
Data Index: 1139000 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.9340. Min Act: -0.1700
Data Index: 1261565 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.9340. Min Act: -0.1700
Data Index: 4105185 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.8715. Min Act: -0.1700
Data Index: 2787823 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.8090. Min Act: -0.1700
Data Index: 6934543 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.8715. Min Act: -0.1700
Data Index: 7788529 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.3715. Min Range: -11.3715
Max Act: 10.8090. Min Act: -0.1700
Data Index: 3728178 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19