Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.4732. Min Act: -0.1700
Data Index: 4252394 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.3482. Min Act: -0.1700
Data Index: 1177101 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.3482. Min Act: -0.1700
Data Index: 5874320 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.2857. Min Act: -0.1700
Data Index: 6902115 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.2857. Min Act: -0.1700
Data Index: 1444063 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.2232. Min Act: -0.1700
Data Index: 6142504 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.1607. Min Act: -0.1700
Data Index: 5143830 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.0982. Min Act: -0.1700
Data Index: 3840684 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4732. Min Range: -8.4732
Max Act: 8.0357. Min Act: -0.1700
Data Index: 1599845 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.8794. Min Act: -0.1700
Data Index: 5429718 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.8794. Min Act: -0.1700
Data Index: 4188170 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.9107. Min Act: -0.1700
Data Index: 4855375 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.7857. Min Act: -0.1700
Data Index: 5571990 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.8169. Min Act: -0.1700
Data Index: 6526988 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.7544. Min Act: -0.1700
Data Index: 6762300 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.7544. Min Act: -0.1700
Data Index: 4941531 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.7544. Min Act: -0.1700
Data Index: 4432475 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.7544. Min Act: -0.1700
Data Index: 7434337 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.7544. Min Act: -0.1700
Data Index: 4952923 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4732. Min Range: -8.4732
Max Act: 7.7232. Min Act: -0.1700
Data Index: 7212447 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19