Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2888 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.2352. Min Act: -0.1700
Data Index: 3054405 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2352. Min Range: -6.2352
Max Act: 6.0165. Min Act: -0.1700
Data Index: 4468724 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.7665. Min Act: -0.1700
Data Index: 5724153 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.6415. Min Act: -0.1700
Data Index: 7874875 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.6102. Min Act: -0.1700
Data Index: 4330265 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.5477. Min Act: -0.1700
Data Index: 8561954 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.5165. Min Act: -0.1700
Data Index: 1409351 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.4852. Min Act: -0.1700
Data Index: 862368 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.4852. Min Act: -0.1700
Data Index: 5068936 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.4540. Min Act: -0.1700
Data Index: 7990342 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.4540. Min Act: -0.1700
Data Index: 7164592 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.4227. Min Act: -0.1700
Data Index: 6304971 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3915. Min Act: -0.1700
Data Index: 8267813 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3602. Min Act: -0.1700
Data Index: 4753721 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3915. Min Act: -0.1700
Data Index: 6039156 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3602. Min Act: -0.1700
Data Index: 3697524 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3602. Min Act: -0.1700
Data Index: 3835601 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3602. Min Act: -0.1700
Data Index: 3576435 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3602. Min Act: -0.1700
Data Index: 8264600 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2352. Min Range: -6.2352
Max Act: 5.3602. Min Act: -0.1700
Data Index: 6551351 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19