Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2288 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2994. Min Range: -6.2994
Max Act: 6.2994. Min Act: -0.1700
Data Index: 4747268 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2994. Min Range: -6.2994
Max Act: 6.2057. Min Act: -0.1700
Data Index: 2767599 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.9557. Min Act: -0.1700
Data Index: 2775077 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.8932. Min Act: -0.1700
Data Index: 4655578 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.7994. Min Act: -0.1700
Data Index: 7821512 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.7682. Min Act: -0.1700
Data Index: 981754 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.7057. Min Act: -0.1700
Data Index: 7281540 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.6744. Min Act: -0.1700
Data Index: 3073798 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.6432. Min Act: -0.1700
Data Index: 1799682 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.5807. Min Act: -0.1700
Data Index: 3730674 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.5807. Min Act: -0.1700
Data Index: 2673495 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.5494. Min Act: -0.1700
Data Index: 3186153 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.5182. Min Act: -0.1700
Data Index: 2553732 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.4869. Min Act: -0.1700
Data Index: 2749963 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.4869. Min Act: -0.1700
Data Index: 5519730 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.4557. Min Act: -0.1700
Data Index: 8375032 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.3932. Min Act: -0.1700
Data Index: 7829965 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.4244. Min Act: -0.1700
Data Index: 3424619 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.4244. Min Act: -0.1700
Data Index: 2767601 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2994. Min Range: -6.2994
Max Act: 5.3932. Min Act: -0.1700
Data Index: 2767602 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19