Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.9870. Min Act: -0.1700
Data Index: 2264761 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.8932. Min Act: -0.1700
Data Index: 2490488 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.8620. Min Act: -0.1700
Data Index: 2708778 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.8307. Min Act: -0.1700
Data Index: 7518420 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.7995. Min Act: -0.1700
Data Index: 2818960 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.7682. Min Act: -0.1700
Data Index: 3876611 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.7682. Min Act: -0.1700
Data Index: 6405700 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.7370. Min Act: -0.1700
Data Index: 69779 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.7057. Min Act: -0.1700
Data Index: 7407441 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6745. Min Act: -0.1700
Data Index: 3814084 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6745. Min Act: -0.1700
Data Index: 5876081 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6745. Min Act: -0.1700
Data Index: 245417 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6745. Min Act: -0.1700
Data Index: 1236995 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6745. Min Act: -0.1700
Data Index: 6896034 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6432. Min Act: -0.1700
Data Index: 3802172 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6432. Min Act: -0.1700
Data Index: 6507250 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6745. Min Act: -0.1700
Data Index: 6737544 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6432. Min Act: -0.1700
Data Index: 7723049 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6432. Min Act: -0.1700
Data Index: 6249553 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9870. Min Range: -4.9870
Max Act: 4.6432. Min Act: -0.1700
Data Index: 4676666 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19