Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2701 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0438. Min Range: -7.0438
Max Act: 7.0438. Min Act: -0.1700
Data Index: 5328006 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.9188. Min Act: -0.1700
Data Index: 8642960 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.8875. Min Act: -0.1700
Data Index: 649852 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.8563. Min Act: -0.1700
Data Index: 6528693 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.8875. Min Act: -0.1700
Data Index: 7781310 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.7625. Min Act: -0.1700
Data Index: 2667156 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.7938. Min Act: -0.1700
Data Index: 495000 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.7625. Min Act: -0.1700
Data Index: 3798986 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.7000. Min Act: -0.1700
Data Index: 2180715 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.7000. Min Act: -0.1700
Data Index: 5033084 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.7313. Min Act: -0.1700
Data Index: 6032676 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.6063. Min Act: -0.1700
Data Index: 4787192 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.6063. Min Act: -0.1700
Data Index: 4819058 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.5438. Min Act: -0.1700
Data Index: 7712349 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.5438. Min Act: -0.1700
Data Index: 5866010 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.5125. Min Act: -0.1700
Data Index: 4988340 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.5125. Min Act: -0.1700
Data Index: 1979905 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.4813. Min Act: -0.1700
Data Index: 5511577 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.4500. Min Act: -0.1700
Data Index: 949483 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0438. Min Range: -7.0438
Max Act: 6.4500. Min Act: -0.1700
Data Index: 4715931 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19