Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4381 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3524. Min Range: -4.3524
Max Act: 4.3524. Min Act: -0.1700
Data Index: 7031965 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3524. Min Range: -4.3524
Max Act: 4.1023. Min Act: -0.1700
Data Index: 8191934 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8835. Min Act: -0.1700
Data Index: 682665 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8835. Min Act: -0.1700
Data Index: 7083822 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8522. Min Act: -0.1700
Data Index: 799644 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8522. Min Act: -0.1700
Data Index: 1877443 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8522. Min Act: -0.1700
Data Index: 1820482 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8522. Min Act: -0.1700
Data Index: 942068 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8210. Min Act: -0.1700
Data Index: 6411658 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8210. Min Act: -0.1700
Data Index: 674602 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.8210. Min Act: -0.1700
Data Index: 8044294 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7897. Min Act: -0.1700
Data Index: 7514658 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7741. Min Act: -0.1700
Data Index: 8462451 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7584. Min Act: -0.1700
Data Index: 1669123 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7741. Min Act: -0.1700
Data Index: 696 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7584. Min Act: -0.1700
Data Index: 545298 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7584. Min Act: -0.1700
Data Index: 8530952 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7428. Min Act: -0.1700
Data Index: 4736292 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7428. Min Act: -0.1700
Data Index: 2840816 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3524. Min Range: -4.3524
Max Act: 3.7428. Min Act: -0.1700
Data Index: 7660229 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19