Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4494 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0627. Min Range: -10.0627
Max Act: 10.0627. Min Act: -0.1700
Data Index: 3654530 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.8752. Min Act: -0.1700
Data Index: 3907184 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.6252. Min Act: -0.1700
Data Index: 7145026 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.6252. Min Act: -0.1700
Data Index: 4190743 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.6252. Min Act: -0.1700
Data Index: 7071049 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.5627. Min Act: -0.1700
Data Index: 3573851 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.4377. Min Act: -0.1700
Data Index: 1415851 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.4377. Min Act: -0.1700
Data Index: 394125 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3752. Min Act: -0.1700
Data Index: 6906428 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3752. Min Act: -0.1700
Data Index: 2470152 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3752. Min Act: -0.1700
Data Index: 537521 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3127. Min Act: -0.1700
Data Index: 7133595 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3752. Min Act: -0.1700
Data Index: 5141425 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3752. Min Act: -0.1700
Data Index: 7536093 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3752. Min Act: -0.1700
Data Index: 1437819 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3127. Min Act: -0.1700
Data Index: 3141130 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.3127. Min Act: -0.1700
Data Index: 5753593 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.2502. Min Act: -0.1700
Data Index: 6706426 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.2502. Min Act: -0.1700
Data Index: 1058593 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0627. Min Range: -10.0627
Max Act: 9.2502. Min Act: -0.1700
Data Index: 6405205 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19