Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.7977. Min Act: -0.1700
Data Index: 5182585 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.7352. Min Act: -0.1700
Data Index: 8002397 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.6727. Min Act: -0.1700
Data Index: 4165752 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.6727. Min Act: -0.1700
Data Index: 4263842 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.5477. Min Act: -0.1700
Data Index: 5382894 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.5477. Min Act: -0.1700
Data Index: 5438892 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.3914. Min Act: -0.1700
Data Index: 8270615 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.3914. Min Act: -0.1700
Data Index: 7094908 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.3602. Min Act: -0.1700
Data Index: 6465442 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.3602. Min Act: -0.1700
Data Index: 8104715 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.3602. Min Act: -0.1700
Data Index: 2257947 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.3602. Min Act: -0.1700
Data Index: 7995402 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2977. Min Act: -0.1700
Data Index: 2254609 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2664. Min Act: -0.1700
Data Index: 375491 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2977. Min Act: -0.1700
Data Index: 3007995 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2977. Min Act: -0.1700
Data Index: 3135233 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2352. Min Act: -0.1700
Data Index: 6661622 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2352. Min Act: -0.1700
Data Index: 1044777 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2352. Min Act: -0.1700
Data Index: 7270215 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7977. Min Range: -7.7977
Max Act: 7.2664. Min Act: -0.1700
Data Index: 8556595 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19