Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4593 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 5522855 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 8692199 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 4809220 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 5972022 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 2110527 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 1721144 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6436. Min Act: -0.1700
Data Index: 184133 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6123. Min Act: -0.1700
Data Index: 2130615 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6123. Min Act: -0.1700
Data Index: 2110530 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6123. Min Act: -0.1700
Data Index: 4234200 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6123. Min Act: -0.1700
Data Index: 4234180 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6123. Min Act: -0.1700
Data Index: 4171917 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.6123. Min Act: -0.1700
Data Index: 8641132 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5498. Min Act: -0.1700
Data Index: 3307139 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5811. Min Act: -0.1700
Data Index: 3861866 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5811. Min Act: -0.1700
Data Index: 8514940 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5498. Min Act: -0.1700
Data Index: 7204922 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5498. Min Act: -0.1700
Data Index: 7570654 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5498. Min Act: -0.1700
Data Index: 3814180 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6436. Min Range: -4.6436
Max Act: 4.5498. Min Act: -0.1700
Data Index: 1395204 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19