Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1359 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.5525. Min Act: -0.1700
Data Index: 263430 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.5369. Min Act: -0.1700
Data Index: 8562312 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.4585. Min Act: -0.1700
Data Index: 7251539 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.4585. Min Act: -0.1700
Data Index: 8504747 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.4429. Min Act: -0.1700
Data Index: 3888323 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.4429. Min Act: -0.1700
Data Index: 5350302 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.4429. Min Act: -0.1700
Data Index: 6632275 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.4115. Min Act: -0.1700
Data Index: 4158638 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.4115. Min Act: -0.1700
Data Index: 717128 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3959. Min Act: -0.1700
Data Index: 4150812 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3645. Min Act: -0.1700
Data Index: 8331516 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3645. Min Act: -0.1700
Data Index: 6026640 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3488. Min Act: -0.1700
Data Index: 7061558 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3488. Min Act: -0.1700
Data Index: 4268288 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3488. Min Act: -0.1700
Data Index: 3904515 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3488. Min Act: -0.1700
Data Index: 7996976 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3645. Min Act: -0.1700
Data Index: 4044409 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3331. Min Act: -0.1700
Data Index: 2917718 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3331. Min Act: -0.1700
Data Index: 5511418 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5525. Min Range: -3.5525
Max Act: 3.3017. Min Act: -0.1700
Data Index: 7435870 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19