Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.5215. Min Act: -0.1700
Data Index: 4200159 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.4903. Min Act: -0.1700
Data Index: 211980 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.4590. Min Act: -0.1700
Data Index: 1321775 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.4903. Min Act: -0.1700
Data Index: 1344862 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.4278. Min Act: -0.1700
Data Index: 3968325 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.4590. Min Act: -0.1700
Data Index: 8547251 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 5697478 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 7726163 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 91324 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 4571165 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 3835506 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3653. Min Act: -0.1700
Data Index: 5672716 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 8012400 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 6077282 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 3716389 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3653. Min Act: -0.1700
Data Index: 1535599 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3653. Min Act: -0.1700
Data Index: 7747563 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3653. Min Act: -0.1700
Data Index: 5130364 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3340. Min Act: -0.1700
Data Index: 7795717 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3653. Min Act: -0.1700
Data Index: 2848675 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19