Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4089 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.5696. Min Act: -0.1700
Data Index: 6913776 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.4446. Min Act: -0.1700
Data Index: 8565748 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.4133. Min Act: -0.1700
Data Index: 7680608 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.4133. Min Act: -0.1700
Data Index: 1395673 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.4133. Min Act: -0.1700
Data Index: 1442053 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.3821. Min Act: -0.1700
Data Index: 874625 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.3821. Min Act: -0.1700
Data Index: 4946477 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.3821. Min Act: -0.1700
Data Index: 5345394 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.3508. Min Act: -0.1700
Data Index: 3701952 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.3196. Min Act: -0.1700
Data Index: 3300472 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.3196. Min Act: -0.1700
Data Index: 3705149 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2883. Min Act: -0.1700
Data Index: 686554 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2883. Min Act: -0.1700
Data Index: 4495394 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.3196. Min Act: -0.1700
Data Index: 4142038 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2883. Min Act: -0.1700
Data Index: 2692481 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2571. Min Act: -0.1700
Data Index: 8313613 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2883. Min Act: -0.1700
Data Index: 7544037 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2571. Min Act: -0.1700
Data Index: 3058989 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2571. Min Act: -0.1700
Data Index: 512071 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5696. Min Range: -5.5696
Max Act: 5.2571. Min Act: -0.1700
Data Index: 2211632 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19