Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2464 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.8548. Min Act: -0.1700
Data Index: 467279 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.9485. Min Act: -0.1700
Data Index: 467278 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.7610. Min Act: -0.1700
Data Index: 7718642 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.7923. Min Act: -0.1700
Data Index: 2803050 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.6985. Min Act: -0.1700
Data Index: 2289079 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.6985. Min Act: -0.1700
Data Index: 1952920 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.6673. Min Act: -0.1700
Data Index: 7718641 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.7298. Min Act: -0.1700
Data Index: 1952919 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.6673. Min Act: -0.1700
Data Index: 4666965 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.6673. Min Act: -0.1700
Data Index: 6737628 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.5735. Min Act: -0.1700
Data Index: 891477 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.6048. Min Act: -0.1700
Data Index: 7792639 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.5423. Min Act: -0.1700
Data Index: 2886851 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.4485. Min Act: -0.1700
Data Index: 4223790 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.4485. Min Act: -0.1700
Data Index: 2948839 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.3860. Min Act: -0.1700
Data Index: 2886852 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.4485. Min Act: -0.1700
Data Index: 5387418 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.3548. Min Act: -0.1700
Data Index: 7718639 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.3860. Min Act: -0.1700
Data Index: 8704799 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9485. Min Range: -4.9485
Max Act: 4.3860. Min Act: -0.1700
Data Index: 2948838 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19