Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4463 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.8310. Min Act: -0.1700
Data Index: 8420488 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.3623. Min Act: -0.1700
Data Index: 4801342 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.3310. Min Act: -0.1700
Data Index: 830675 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.3310. Min Act: -0.1700
Data Index: 4440753 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.2060. Min Act: -0.1700
Data Index: 1536069 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.1748. Min Act: -0.1700
Data Index: 5375432 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.1748. Min Act: -0.1700
Data Index: 4688985 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.1435. Min Act: -0.1700
Data Index: 6726794 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.1123. Min Act: -0.1700
Data Index: 2804161 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.0810. Min Act: -0.1700
Data Index: 6578488 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.0498. Min Act: -0.1700
Data Index: 5548546 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.0498. Min Act: -0.1700
Data Index: 8743427 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.0498. Min Act: -0.1700
Data Index: 6268926 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8310. Min Range: -6.8310
Max Act: 6.0185. Min Act: -0.1700
Data Index: 1325129 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8310. Min Range: -6.8310
Max Act: 5.9873. Min Act: -0.1700
Data Index: 5117715 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8310. Min Range: -6.8310
Max Act: 5.9873. Min Act: -0.1700
Data Index: 4356806 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8310. Min Range: -6.8310
Max Act: 5.9248. Min Act: -0.1700
Data Index: 6276850 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8310. Min Range: -6.8310
Max Act: 5.8935. Min Act: -0.1700
Data Index: 5694543 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8310. Min Range: -6.8310
Max Act: 5.8623. Min Act: -0.1700
Data Index: 2071451 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8310. Min Range: -6.8310
Max Act: 5.8310. Min Act: -0.1700
Data Index: 5177688 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19