Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2916 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0533. Min Range: -5.0533
Max Act: 5.0533. Min Act: -0.1700
Data Index: 571181 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.9908. Min Act: -0.1700
Data Index: 6704996 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.9596. Min Act: -0.1700
Data Index: 2400187 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.9596. Min Act: -0.1700
Data Index: 5597437 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8971. Min Act: -0.1700
Data Index: 2732617 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8658. Min Act: -0.1700
Data Index: 5418883 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8658. Min Act: -0.1700
Data Index: 4012684 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8658. Min Act: -0.1700
Data Index: 7788170 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8658. Min Act: -0.1700
Data Index: 2309629 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8971. Min Act: -0.1700
Data Index: 1048497 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8033. Min Act: -0.1700
Data Index: 4456306 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8346. Min Act: -0.1700
Data Index: 6262788 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8033. Min Act: -0.1700
Data Index: 4408395 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8346. Min Act: -0.1700
Data Index: 3802404 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8033. Min Act: -0.1700
Data Index: 5105574 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 2561110 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 3954188 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 1976262 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.8033. Min Act: -0.1700
Data Index: 5150879 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0533. Min Range: -5.0533
Max Act: 4.7721. Min Act: -0.1700
Data Index: 8751722 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19