Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.9012. Min Act: -0.1700
Data Index: 961001 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.8075. Min Act: -0.1700
Data Index: 1797848 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.7762. Min Act: -0.1700
Data Index: 5088587 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.6512. Min Act: -0.1700
Data Index: 4693594 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.6200. Min Act: -0.1700
Data Index: 4455237 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.6200. Min Act: -0.1700
Data Index: 603765 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.5575. Min Act: -0.1700
Data Index: 3767497 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4950. Min Act: -0.1700
Data Index: 5716897 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4637. Min Act: -0.1700
Data Index: 1327635 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4637. Min Act: -0.1700
Data Index: 7399413 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4637. Min Act: -0.1700
Data Index: 1166355 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4637. Min Act: -0.1700
Data Index: 4487374 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4012. Min Act: -0.1700
Data Index: 527438 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.3700. Min Act: -0.1700
Data Index: 3315489 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4012. Min Act: -0.1700
Data Index: 3756229 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4012. Min Act: -0.1700
Data Index: 8073230 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4012. Min Act: -0.1700
Data Index: 6425864 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.4012. Min Act: -0.1700
Data Index: 6324880 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.3700. Min Act: -0.1700
Data Index: 770923 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9012. Min Range: -6.9012
Max Act: 6.3387. Min Act: -0.1700
Data Index: 5414377 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19