Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5218 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.6452. Min Act: -0.1700
Data Index: 6762422 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.6452. Min Act: -0.1700
Data Index: 2369178 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.5202. Min Act: -0.1700
Data Index: 52025 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4890. Min Act: -0.1700
Data Index: 52041 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4890. Min Act: -0.1700
Data Index: 5820012 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4890. Min Act: -0.1700
Data Index: 3257034 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4265. Min Act: -0.1700
Data Index: 2369179 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4265. Min Act: -0.1700
Data Index: 1791144 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4265. Min Act: -0.1700
Data Index: 3066173 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4265. Min Act: -0.1700
Data Index: 360137 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4265. Min Act: -0.1700
Data Index: 4772298 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4265. Min Act: -0.1700
Data Index: 2369177 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.3952. Min Act: -0.1700
Data Index: 3642472 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.4265. Min Act: -0.1700
Data Index: 6647462 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.3952. Min Act: -0.1700
Data Index: 4673290 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.3952. Min Act: -0.1700
Data Index: 7637842 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.3640. Min Act: -0.1700
Data Index: 6815769 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.3640. Min Act: -0.1700
Data Index: 3865896 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.3327. Min Act: -0.1700
Data Index: 2238907 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6452. Min Range: -4.6452
Max Act: 4.3640. Min Act: -0.1700
Data Index: 6392555 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19