Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 265 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.3721. Min Act: -0.1700
Data Index: 6288845 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.3016. Min Act: -0.1700
Data Index: 4407493 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.3016. Min Act: -0.1700
Data Index: 3116581 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2663. Min Act: -0.1700
Data Index: 5360413 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2663. Min Act: -0.1700
Data Index: 2687561 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2663. Min Act: -0.1700
Data Index: 1007528 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2663. Min Act: -0.1700
Data Index: 4245918 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2486. Min Act: -0.1700
Data Index: 2687568 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2486. Min Act: -0.1700
Data Index: 8805753 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2310. Min Act: -0.1700
Data Index: 2880280 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2486. Min Act: -0.1700
Data Index: 2687565 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2310. Min Act: -0.1700
Data Index: 2687583 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2486. Min Act: -0.1700
Data Index: 4961021 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2310. Min Act: -0.1700
Data Index: 1310975 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2134. Min Act: -0.1700
Data Index: 4325033 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2310. Min Act: -0.1700
Data Index: 1583180 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2310. Min Act: -0.1700
Data Index: 7273908 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2310. Min Act: -0.1700
Data Index: 2521975 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2134. Min Act: -0.1700
Data Index: 3425573 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3721. Min Range: -1.3721
Max Act: 1.2310. Min Act: -0.1700
Data Index: 2687584 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19