Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2375 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.2817. Min Act: -0.1700
Data Index: 2952695 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.2505. Min Act: -0.1700
Data Index: 5682614 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.2192. Min Act: -0.1700
Data Index: 1110986 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.2192. Min Act: -0.1700
Data Index: 8326298 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.2192. Min Act: -0.1700
Data Index: 477609 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.2192. Min Act: -0.1700
Data Index: 6036852 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1880. Min Act: -0.1700
Data Index: 2787872 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1880. Min Act: -0.1700
Data Index: 139046 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1880. Min Act: -0.1700
Data Index: 3074408 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 1516862 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 8121729 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 311121 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 3711875 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 635056 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 1305311 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 8357762 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 8652290 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1567. Min Act: -0.1700
Data Index: 2985198 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1255. Min Act: -0.1700
Data Index: 1869116 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2817. Min Range: -5.2817
Max Act: 5.1255. Min Act: -0.1700
Data Index: 5733453 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19