Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 184 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.9422. Min Act: -0.1700
Data Index: 3599561 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.5672. Min Act: -0.1700
Data Index: 1027683 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.5360. Min Act: -0.1700
Data Index: 7098369 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.5047. Min Act: -0.1700
Data Index: 1391101 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.4110. Min Act: -0.1700
Data Index: 2421256 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.4110. Min Act: -0.1700
Data Index: 1432773 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.3797. Min Act: -0.1700
Data Index: 1418702 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.3797. Min Act: -0.1700
Data Index: 8127023 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.3485. Min Act: -0.1700
Data Index: 6207271 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.3172. Min Act: -0.1700
Data Index: 2724166 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2860. Min Act: -0.1700
Data Index: 8803735 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2547. Min Act: -0.1700
Data Index: 5590988 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2235. Min Act: -0.1700
Data Index: 1696029 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2547. Min Act: -0.1700
Data Index: 2530598 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2860. Min Act: -0.1700
Data Index: 1471019 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2235. Min Act: -0.1700
Data Index: 6773151 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2235. Min Act: -0.1700
Data Index: 4059751 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.2235. Min Act: -0.1700
Data Index: 7745561 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.1922. Min Act: -0.1700
Data Index: 2014429 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9422. Min Range: -7.9422
Max Act: 7.1922. Min Act: -0.1700
Data Index: 6657600 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #19