Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4460 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.4163. Min Range: -14.4163
Max Act: 14.4163. Min Act: -0.1700
Data Index: 614914 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.4163. Min Range: -14.4163
Max Act: 14.4163. Min Act: -0.1700
Data Index: 501328 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.4163. Min Range: -14.4163
Max Act: 14.1663. Min Act: -0.1700
Data Index: 2664325 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.4163. Min Range: -14.4163
Max Act: 14.0413. Min Act: -0.1700
Data Index: 7834839 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.4163. Min Range: -14.4163
Max Act: 14.0413. Min Act: -0.1700
Data Index: 4470570 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.9788. Min Act: -0.1700
Data Index: 4573209 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.7288. Min Act: -0.1700
Data Index: 7760956 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.7288. Min Act: -0.1700
Data Index: 3302156 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 6196051 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 5652038 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 2080144 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 6651396 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 1447655 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 748341 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 1415626 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.6038. Min Act: -0.1700
Data Index: 690106 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.5413. Min Act: -0.1700
Data Index: 503773 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.5413. Min Act: -0.1700
Data Index: 7966165 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.5413. Min Act: -0.1700
Data Index: 6163084 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.4163. Min Range: -14.4163
Max Act: 13.5413. Min Act: -0.1700
Data Index: 4246859 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19