Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.4374. Min Act: -0.1700
Data Index: 7580207 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.3437. Min Act: -0.1700
Data Index: 8645205 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.2499. Min Act: -0.1700
Data Index: 106445 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.2187. Min Act: -0.1700
Data Index: 1121048 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.2499. Min Act: -0.1700
Data Index: 951100 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.1874. Min Act: -0.1700
Data Index: 6246717 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.1562. Min Act: -0.1700
Data Index: 3215867 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0937. Min Act: -0.1700
Data Index: 6008494 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0937. Min Act: -0.1700
Data Index: 4299935 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0624. Min Act: -0.1700
Data Index: 3639644 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0624. Min Act: -0.1700
Data Index: 2811484 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0312. Min Act: -0.1700
Data Index: 236359 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0312. Min Act: -0.1700
Data Index: 6594604 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0312. Min Act: -0.1700
Data Index: 313660 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0312. Min Act: -0.1700
Data Index: 6298881 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9999. Min Act: -0.1700
Data Index: 5831574 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8526044 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4374. Min Range: -5.4374
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8277432 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9999. Min Act: -0.1700
Data Index: 7519000 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4374. Min Range: -5.4374
Max Act: 4.9374. Min Act: -0.1700
Data Index: 6476273 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19