Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.3425. Min Act: -0.1700
Data Index: 7450493 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.2488. Min Act: -0.1700
Data Index: 3458884 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.1863. Min Act: -0.1700
Data Index: 4291935 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.1863. Min Act: -0.1700
Data Index: 8279437 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.1550. Min Act: -0.1700
Data Index: 7072903 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.1550. Min Act: -0.1700
Data Index: 485836 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0925. Min Act: -0.1700
Data Index: 3175151 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0925. Min Act: -0.1700
Data Index: 5501169 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0925. Min Act: -0.1700
Data Index: 5486064 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0612. Min Act: -0.1700
Data Index: 8103041 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0612. Min Act: -0.1700
Data Index: 2836195 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0300. Min Act: -0.1700
Data Index: 8730595 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0300. Min Act: -0.1700
Data Index: 3168253 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0300. Min Act: -0.1700
Data Index: 4152735 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0300. Min Act: -0.1700
Data Index: 2924207 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0300. Min Act: -0.1700
Data Index: 1166894 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0300. Min Act: -0.1700
Data Index: 2765908 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3425. Min Range: -4.3425
Max Act: 4.0300. Min Act: -0.1700
Data Index: 557019 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3425. Min Range: -4.3425
Max Act: 3.9987. Min Act: -0.1700
Data Index: 1163526 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3425. Min Range: -4.3425
Max Act: 3.9675. Min Act: -0.1700
Data Index: 3768792 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19