Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.5119. Min Act: -0.1700
Data Index: 7527223 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.4181. Min Act: -0.1700
Data Index: 4370048 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.2931. Min Act: -0.1700
Data Index: 3611391 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.2306. Min Act: -0.1700
Data Index: 8586964 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1994. Min Act: -0.1700
Data Index: 3200349 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1994. Min Act: -0.1700
Data Index: 7951708 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1369. Min Act: -0.1700
Data Index: 4091937 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1681. Min Act: -0.1700
Data Index: 849298 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1681. Min Act: -0.1700
Data Index: 2319794 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1369. Min Act: -0.1700
Data Index: 6090934 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1369. Min Act: -0.1700
Data Index: 1115811 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1369. Min Act: -0.1700
Data Index: 7377282 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1056. Min Act: -0.1700
Data Index: 6487396 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1056. Min Act: -0.1700
Data Index: 4765931 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.1056. Min Act: -0.1700
Data Index: 2810818 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.0744. Min Act: -0.1700
Data Index: 8160509 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.0431. Min Act: -0.1700
Data Index: 589150 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.0119. Min Act: -0.1700
Data Index: 5101733 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.0119. Min Act: -0.1700
Data Index: 8431269 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5119. Min Range: -6.5119
Max Act: 6.0431. Min Act: -0.1700
Data Index: 8098715 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19