Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6340 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4682. Min Range: -7.4682
Max Act: 7.4682. Min Act: -0.1700
Data Index: 7344813 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4682. Min Range: -7.4682
Max Act: 7.4057. Min Act: -0.1700
Data Index: 1618379 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.9995. Min Act: -0.1700
Data Index: 1046161 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.9682. Min Act: -0.1700
Data Index: 1013472 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.8745. Min Act: -0.1700
Data Index: 6753888 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.7807. Min Act: -0.1700
Data Index: 2461729 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.7807. Min Act: -0.1700
Data Index: 3556531 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.7807. Min Act: -0.1700
Data Index: 4606793 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.7807. Min Act: -0.1700
Data Index: 8086476 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.7182. Min Act: -0.1700
Data Index: 112344 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.6557. Min Act: -0.1700
Data Index: 4594896 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.6557. Min Act: -0.1700
Data Index: 705493 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.6557. Min Act: -0.1700
Data Index: 3929516 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.6557. Min Act: -0.1700
Data Index: 8498361 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.6245. Min Act: -0.1700
Data Index: 5918867 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.6245. Min Act: -0.1700
Data Index: 6523374 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.6557. Min Act: -0.1700
Data Index: 6844984 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.5932. Min Act: -0.1700
Data Index: 4809255 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.5932. Min Act: -0.1700
Data Index: 3597968 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4682. Min Range: -7.4682
Max Act: 6.5620. Min Act: -0.1700
Data Index: 3539841 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19