Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5705 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.6396. Min Act: -0.1700
Data Index: 7990526 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.5146. Min Act: -0.1700
Data Index: 8103598 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.4521. Min Act: -0.1700
Data Index: 3130940 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.3896. Min Act: -0.1700
Data Index: 4202505 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.3271. Min Act: -0.1700
Data Index: 5894578 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.3271. Min Act: -0.1700
Data Index: 434184 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.2646. Min Act: -0.1700
Data Index: 8386141 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.2646. Min Act: -0.1700
Data Index: 5049192 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.2646. Min Act: -0.1700
Data Index: 4241889 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.2646. Min Act: -0.1700
Data Index: 765064 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.2021. Min Act: -0.1700
Data Index: 4826923 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.2021. Min Act: -0.1700
Data Index: 3912330 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.2646. Min Act: -0.1700
Data Index: 2455164 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.1396. Min Act: -0.1700
Data Index: 1342992 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.1396. Min Act: -0.1700
Data Index: 6042283 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.1396. Min Act: -0.1700
Data Index: 4486828 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.1396. Min Act: -0.1700
Data Index: 6885267 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.1396. Min Act: -0.1700
Data Index: 6204336 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.0771. Min Act: -0.1700
Data Index: 2811145 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6396. Min Range: -10.6396
Max Act: 10.0771. Min Act: -0.1700
Data Index: 3101317 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19