Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5869 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.5307. Min Act: -0.1700
Data Index: 3755119 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.4057. Min Act: -0.1700
Data Index: 6239426 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.4057. Min Act: -0.1700
Data Index: 4652468 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.3745. Min Act: -0.1700
Data Index: 7381104 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.3745. Min Act: -0.1700
Data Index: 4589226 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.3745. Min Act: -0.1700
Data Index: 8679568 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.3745. Min Act: -0.1700
Data Index: 7391401 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.3432. Min Act: -0.1700
Data Index: 3312368 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7632063 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.3432. Min Act: -0.1700
Data Index: 8160124 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2807. Min Act: -0.1700
Data Index: 3672684 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2495. Min Act: -0.1700
Data Index: 8505266 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2807. Min Act: -0.1700
Data Index: 6274416 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2807. Min Act: -0.1700
Data Index: 5450897 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2807. Min Act: -0.1700
Data Index: 8067869 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2807. Min Act: -0.1700
Data Index: 2459151 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2495. Min Act: -0.1700
Data Index: 5788873 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2495. Min Act: -0.1700
Data Index: 3029601 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2495. Min Act: -0.1700
Data Index: 2969531 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5307. Min Range: -5.5307
Max Act: 5.2182. Min Act: -0.1700
Data Index: 5011459 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19