Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1389 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3089. Min Range: -6.3089
Max Act: 6.3089. Min Act: -0.1700
Data Index: 1858896 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3089. Min Range: -6.3089
Max Act: 6.1527. Min Act: -0.1700
Data Index: 5795064 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3089. Min Range: -6.3089
Max Act: 6.0902. Min Act: -0.1700
Data Index: 5507737 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3089. Min Range: -6.3089
Max Act: 6.1214. Min Act: -0.1700
Data Index: 633600 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.9964. Min Act: -0.1700
Data Index: 4001737 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.9652. Min Act: -0.1700
Data Index: 317299 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.9027. Min Act: -0.1700
Data Index: 4589123 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.9027. Min Act: -0.1700
Data Index: 5961654 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7777. Min Act: -0.1700
Data Index: 8809737 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.8089. Min Act: -0.1700
Data Index: 7214500 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.8089. Min Act: -0.1700
Data Index: 1510961 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7777. Min Act: -0.1700
Data Index: 4937481 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7777. Min Act: -0.1700
Data Index: 6599135 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7464. Min Act: -0.1700
Data Index: 7292937 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3168742 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7464. Min Act: -0.1700
Data Index: 1048689 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3379002 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7464. Min Act: -0.1700
Data Index: 3303149 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7152. Min Act: -0.1700
Data Index: 616830 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3089. Min Range: -6.3089
Max Act: 5.7152. Min Act: -0.1700
Data Index: 7212068 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19