Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.4700. Min Act: -0.1700
Data Index: 4706645 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.4700. Min Act: -0.1700
Data Index: 1112808 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.2825. Min Act: -0.1700
Data Index: 7639227 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.2512. Min Act: -0.1700
Data Index: 1942185 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.2512. Min Act: -0.1700
Data Index: 7257955 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.2200. Min Act: -0.1700
Data Index: 155184 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.2200. Min Act: -0.1700
Data Index: 3934267 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.1575. Min Act: -0.1700
Data Index: 5882471 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.1262. Min Act: -0.1700
Data Index: 74860 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.0950. Min Act: -0.1700
Data Index: 6938197 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.0325. Min Act: -0.1700
Data Index: 7049887 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.0325. Min Act: -0.1700
Data Index: 2993465 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.0012. Min Act: -0.1700
Data Index: 2635145 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4700. Min Range: -6.4700
Max Act: 6.0012. Min Act: -0.1700
Data Index: 5723974 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4700. Min Range: -6.4700
Max Act: 5.9387. Min Act: -0.1700
Data Index: 2424960 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4700. Min Range: -6.4700
Max Act: 5.9700. Min Act: -0.1700
Data Index: 2514896 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4700. Min Range: -6.4700
Max Act: 5.9700. Min Act: -0.1700
Data Index: 1681252 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4700. Min Range: -6.4700
Max Act: 5.9700. Min Act: -0.1700
Data Index: 2426168 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4700. Min Range: -6.4700
Max Act: 5.9387. Min Act: -0.1700
Data Index: 8760799 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4700. Min Range: -6.4700
Max Act: 5.9075. Min Act: -0.1700
Data Index: 4235974 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19