Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1629 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.5379. Min Act: -0.1700
Data Index: 7455845 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.4129. Min Act: -0.1700
Data Index: 5201957 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.3817. Min Act: -0.1700
Data Index: 5610362 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.3192. Min Act: -0.1700
Data Index: 2659390 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.2567. Min Act: -0.1700
Data Index: 209262 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.2567. Min Act: -0.1700
Data Index: 4027204 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1629. Min Act: -0.1700
Data Index: 3429635 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1629. Min Act: -0.1700
Data Index: 6284328 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1317. Min Act: -0.1700
Data Index: 6587777 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1317. Min Act: -0.1700
Data Index: 6526421 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1317. Min Act: -0.1700
Data Index: 1503673 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1317. Min Act: -0.1700
Data Index: 3421521 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1317. Min Act: -0.1700
Data Index: 3575247 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1004. Min Act: -0.1700
Data Index: 6625424 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1004. Min Act: -0.1700
Data Index: 3266869 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1004. Min Act: -0.1700
Data Index: 8255125 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.0379. Min Act: -0.1700
Data Index: 7537691 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1004. Min Act: -0.1700
Data Index: 4371933 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.1004. Min Act: -0.1700
Data Index: 7307086 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5379. Min Range: -4.5379
Max Act: 4.0691. Min Act: -0.1700
Data Index: 4580963 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19