Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.5838. Min Act: -0.1700
Data Index: 180316 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.5838. Min Act: -0.1700
Data Index: 3479725 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.3963. Min Act: -0.1700
Data Index: 2249131 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.3338. Min Act: -0.1700
Data Index: 6836287 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.2713. Min Act: -0.1700
Data Index: 8340031 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.2401. Min Act: -0.1700
Data Index: 8744499 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.2401. Min Act: -0.1700
Data Index: 4936410 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.2088. Min Act: -0.1700
Data Index: 633711 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.2088. Min Act: -0.1700
Data Index: 8568049 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.1463. Min Act: -0.1700
Data Index: 7902663 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.1463. Min Act: -0.1700
Data Index: 8367217 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.1151. Min Act: -0.1700
Data Index: 5517910 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.0526. Min Act: -0.1700
Data Index: 6873519 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.0213. Min Act: -0.1700
Data Index: 3910852 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.0213. Min Act: -0.1700
Data Index: 1711760 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.0213. Min Act: -0.1700
Data Index: 8451136 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5838. Min Range: -8.5838
Max Act: 8.0213. Min Act: -0.1700
Data Index: 792324 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5838. Min Range: -8.5838
Max Act: 7.9901. Min Act: -0.1700
Data Index: 292464 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5838. Min Range: -8.5838
Max Act: 7.9588. Min Act: -0.1700
Data Index: 1213596 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5838. Min Range: -8.5838
Max Act: 7.9588. Min Act: -0.1700
Data Index: 102179 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19