Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.6441. Min Act: -0.1700
Data Index: 5681933 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.6120. Min Act: -0.1700
Data Index: 397213 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.5798. Min Act: -0.1700
Data Index: 962615 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.6120. Min Act: -0.1700
Data Index: 632990 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.5798. Min Act: -0.1700
Data Index: 225950 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.5798. Min Act: -0.1700
Data Index: 1717223 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.5313. Min Act: -0.1700
Data Index: 8254213 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.5636. Min Act: -0.1700
Data Index: 397212 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.5313. Min Act: -0.1700
Data Index: 5813435 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.5152. Min Act: -0.1700
Data Index: 5505192 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4990. Min Act: -0.1700
Data Index: 8071274 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4828. Min Act: -0.1700
Data Index: 1906695 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4503. Min Act: -0.1700
Data Index: 5462579 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4828. Min Act: -0.1700
Data Index: 8629618 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4665. Min Act: -0.1700
Data Index: 1082573 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4665. Min Act: -0.1700
Data Index: 247426 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4990. Min Act: -0.1700
Data Index: 4242817 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4828. Min Act: -0.1700
Data Index: 2573215 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4503. Min Act: -0.1700
Data Index: 1001334 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6441. Min Range: -2.6441
Max Act: 2.4503. Min Act: -0.1700
Data Index: 1877455 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19