Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1565 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.2780. Min Act: -0.1700
Data Index: 6791620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.2622. Min Act: -0.1700
Data Index: 8290761 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.2465. Min Act: -0.1700
Data Index: 1812826 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.2465. Min Act: -0.1700
Data Index: 8487179 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.2151. Min Act: -0.1700
Data Index: 2938642 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.2151. Min Act: -0.1700
Data Index: 6846018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1994. Min Act: -0.1700
Data Index: 1793541 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1994. Min Act: -0.1700
Data Index: 5953554 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1837. Min Act: -0.1700
Data Index: 4465497 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1837. Min Act: -0.1700
Data Index: 3334738 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1679. Min Act: -0.1700
Data Index: 5637480 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1679. Min Act: -0.1700
Data Index: 8608471 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1522. Min Act: -0.1700
Data Index: 6202379 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1522. Min Act: -0.1700
Data Index: 4784123 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1522. Min Act: -0.1700
Data Index: 7381379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1364. Min Act: -0.1700
Data Index: 1542908 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1522. Min Act: -0.1700
Data Index: 6992286 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1522. Min Act: -0.1700
Data Index: 8224499 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1364. Min Act: -0.1700
Data Index: 7323358 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2780. Min Range: -3.2780
Max Act: 3.1364. Min Act: -0.1700
Data Index: 7713895 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19