Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1023 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2287. Min Range: -8.2287
Max Act: 8.2287. Min Act: -0.1700
Data Index: 4459458 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2287. Min Range: -8.2287
Max Act: 8.2287. Min Act: -0.1700
Data Index: 230499 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.9474. Min Act: -0.1700
Data Index: 5652320 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.7599. Min Act: -0.1700
Data Index: 961461 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.7287. Min Act: -0.1700
Data Index: 7745093 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.6974. Min Act: -0.1700
Data Index: 2550627 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.5724. Min Act: -0.1700
Data Index: 7760805 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.5412. Min Act: -0.1700
Data Index: 5136717 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.5099. Min Act: -0.1700
Data Index: 4150517 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.4474. Min Act: -0.1700
Data Index: 7824291 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.4474. Min Act: -0.1700
Data Index: 2106349 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.4474. Min Act: -0.1700
Data Index: 7967739 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.4162. Min Act: -0.1700
Data Index: 6769183 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.4162. Min Act: -0.1700
Data Index: 6540114 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.3537. Min Act: -0.1700
Data Index: 3820187 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.2912. Min Act: -0.1700
Data Index: 1442428 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.3224. Min Act: -0.1700
Data Index: 2458409 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.2599. Min Act: -0.1700
Data Index: 5611962 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.2287. Min Act: -0.1700
Data Index: 2459599 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2287. Min Range: -8.2287
Max Act: 7.1974. Min Act: -0.1700
Data Index: 2944787 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19