Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2381 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.3528. Min Act: -0.1700
Data Index: 2143517 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.2278. Min Act: -0.1700
Data Index: 2949782 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.1965. Min Act: -0.1700
Data Index: 223676 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.1653. Min Act: -0.1700
Data Index: 1141398 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.1340. Min Act: -0.1700
Data Index: 5874385 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.0715. Min Act: -0.1700
Data Index: 7245959 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.0715. Min Act: -0.1700
Data Index: 15652 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.0715. Min Act: -0.1700
Data Index: 6022298 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.0403. Min Act: -0.1700
Data Index: 3715021 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.0090. Min Act: -0.1700
Data Index: 3839401 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.0090. Min Act: -0.1700
Data Index: 3279151 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3528. Min Range: -5.3528
Max Act: 5.0090. Min Act: -0.1700
Data Index: 5895542 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9778. Min Act: -0.1700
Data Index: 5928527 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9778. Min Act: -0.1700
Data Index: 3032471 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9465. Min Act: -0.1700
Data Index: 4390198 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9465. Min Act: -0.1700
Data Index: 8756958 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9465. Min Act: -0.1700
Data Index: 4128000 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9465. Min Act: -0.1700
Data Index: 6509862 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9778. Min Act: -0.1700
Data Index: 1844137 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3528. Min Range: -5.3528
Max Act: 4.9153. Min Act: -0.1700
Data Index: 6336350 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19