Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2662 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.9345. Min Act: -0.1700
Data Index: 6828920 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.9345. Min Act: -0.1700
Data Index: 6064674 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.8095. Min Act: -0.1700
Data Index: 5480646 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.6533. Min Act: -0.1700
Data Index: 1196750 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5908. Min Act: -0.1700
Data Index: 5240910 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5595. Min Act: -0.1700
Data Index: 2627285 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5595. Min Act: -0.1700
Data Index: 4371481 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5595. Min Act: -0.1700
Data Index: 3097794 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5283. Min Act: -0.1700
Data Index: 1030882 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5283. Min Act: -0.1700
Data Index: 7635722 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5283. Min Act: -0.1700
Data Index: 1366363 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.5283. Min Act: -0.1700
Data Index: 5240918 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4970. Min Act: -0.1700
Data Index: 853387 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4970. Min Act: -0.1700
Data Index: 8495188 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4970. Min Act: -0.1700
Data Index: 2269213 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4970. Min Act: -0.1700
Data Index: 5184243 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4658. Min Act: -0.1700
Data Index: 5240907 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4658. Min Act: -0.1700
Data Index: 1731325 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4658. Min Act: -0.1700
Data Index: 5711374 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9345. Min Range: -4.9345
Max Act: 4.4658. Min Act: -0.1700
Data Index: 5240898 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19