Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.4556. Min Act: -0.1700
Data Index: 227388 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.3931. Min Act: -0.1700
Data Index: 6410313 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.4244. Min Act: -0.1700
Data Index: 227387 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.3619. Min Act: -0.1700
Data Index: 2609958 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.3619. Min Act: -0.1700
Data Index: 5135563 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.3619. Min Act: -0.1700
Data Index: 7926855 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.3619. Min Act: -0.1700
Data Index: 261596 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2994. Min Act: -0.1700
Data Index: 5331798 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2681. Min Act: -0.1700
Data Index: 7255828 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2681. Min Act: -0.1700
Data Index: 5135562 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2056. Min Act: -0.1700
Data Index: 281590 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2681. Min Act: -0.1700
Data Index: 281589 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2369. Min Act: -0.1700
Data Index: 3986378 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2681. Min Act: -0.1700
Data Index: 5522533 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2369. Min Act: -0.1700
Data Index: 1354804 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2056. Min Act: -0.1700
Data Index: 5472925 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2056. Min Act: -0.1700
Data Index: 2647114 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2056. Min Act: -0.1700
Data Index: 5498772 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2369. Min Act: -0.1700
Data Index: 5498779 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4556. Min Range: -5.4556
Max Act: 5.2056. Min Act: -0.1700
Data Index: 2050159 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19