Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 745 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.2582. Min Act: -0.1700
Data Index: 5953732 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.1957. Min Act: -0.1700
Data Index: 6812687 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.1645. Min Act: -0.1700
Data Index: 5647572 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.1332. Min Act: -0.1700
Data Index: 1155068 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.1332. Min Act: -0.1700
Data Index: 8220694 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.1020. Min Act: -0.1700
Data Index: 6656132 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.1020. Min Act: -0.1700
Data Index: 2397958 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.1020. Min Act: -0.1700
Data Index: 6836237 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.0707. Min Act: -0.1700
Data Index: 3044673 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.0395. Min Act: -0.1700
Data Index: 1985629 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.0707. Min Act: -0.1700
Data Index: 1155070 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.0082. Min Act: -0.1700
Data Index: 1155067 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.0082. Min Act: -0.1700
Data Index: 6836236 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2582. Min Range: -5.2582
Max Act: 5.0082. Min Act: -0.1700
Data Index: 7135431 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2582. Min Range: -5.2582
Max Act: 4.9770. Min Act: -0.1700
Data Index: 7846586 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2582. Min Range: -5.2582
Max Act: 4.9770. Min Act: -0.1700
Data Index: 5585011 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2582. Min Range: -5.2582
Max Act: 4.9770. Min Act: -0.1700
Data Index: 6628800 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2582. Min Range: -5.2582
Max Act: 4.9457. Min Act: -0.1700
Data Index: 7388323 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2582. Min Range: -5.2582
Max Act: 4.9457. Min Act: -0.1700
Data Index: 6812686 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2582. Min Range: -5.2582
Max Act: 4.9457. Min Act: -0.1700
Data Index: 7135432 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #19