Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1902 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.6736. Min Act: -0.1700
Data Index: 2437090 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.6736. Min Act: -0.1700
Data Index: 689094 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.5174. Min Act: -0.1700
Data Index: 3458850 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3924. Min Act: -0.1700
Data Index: 504527 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3924. Min Act: -0.1700
Data Index: 282451 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3924. Min Act: -0.1700
Data Index: 5866410 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3611. Min Act: -0.1700
Data Index: 2335158 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.2986. Min Act: -0.1700
Data Index: 7537170 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 5048513 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 2398873 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.2986. Min Act: -0.1700
Data Index: 1849871 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 908451 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 1880454 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 4856264 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 1615364 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 7177488 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 6824408 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.2986. Min Act: -0.1700
Data Index: 2148267 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.2986. Min Act: -0.1700
Data Index: 1060114 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6736. Min Range: -4.6736
Max Act: 4.3299. Min Act: -0.1700
Data Index: 7240267 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19