Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2014 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.4810. Min Act: -0.1700
Data Index: 6918823 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.4497. Min Act: -0.1700
Data Index: 3620508 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.4497. Min Act: -0.1700
Data Index: 6380646 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.4497. Min Act: -0.1700
Data Index: 2893429 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.3872. Min Act: -0.1700
Data Index: 6148272 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.3872. Min Act: -0.1700
Data Index: 2489463 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.3247. Min Act: -0.1700
Data Index: 7014916 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.2935. Min Act: -0.1700
Data Index: 3191145 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1997. Min Act: -0.1700
Data Index: 5686257 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1997. Min Act: -0.1700
Data Index: 5035108 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1997. Min Act: -0.1700
Data Index: 3835433 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.2310. Min Act: -0.1700
Data Index: 5082998 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1685. Min Act: -0.1700
Data Index: 1584545 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1372. Min Act: -0.1700
Data Index: 120597 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1685. Min Act: -0.1700
Data Index: 8001236 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1372. Min Act: -0.1700
Data Index: 2983358 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1060. Min Act: -0.1700
Data Index: 6772790 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.0747. Min Act: -0.1700
Data Index: 3951652 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.1060. Min Act: -0.1700
Data Index: 6819326 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4810. Min Range: -6.4810
Max Act: 6.0747. Min Act: -0.1700
Data Index: 8356415 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19