Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1361 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.9679. Min Act: -0.1700
Data Index: 1583 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.8428. Min Act: -0.1700
Data Index: 3537784 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7803. Min Act: -0.1700
Data Index: 4832020 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7177. Min Act: -0.1700
Data Index: 1104616 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.7177. Min Act: -0.1700
Data Index: 4391273 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6865. Min Act: -0.1700
Data Index: 931926 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6865. Min Act: -0.1700
Data Index: 3313680 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6865. Min Act: -0.1700
Data Index: 954567 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6552. Min Act: -0.1700
Data Index: 5618419 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6865. Min Act: -0.1700
Data Index: 5744207 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6239. Min Act: -0.1700
Data Index: 6791433 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6239. Min Act: -0.1700
Data Index: 1204301 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6239. Min Act: -0.1700
Data Index: 1186646 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6239. Min Act: -0.1700
Data Index: 2531256 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.5926. Min Act: -0.1700
Data Index: 2242931 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6239. Min Act: -0.1700
Data Index: 7914240 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.6239. Min Act: -0.1700
Data Index: 6871644 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.5926. Min Act: -0.1700
Data Index: 40255 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.5613. Min Act: -0.1700
Data Index: 6074139 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9679. Min Range: -3.9679
Max Act: 3.5613. Min Act: -0.1700
Data Index: 6670613 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19