Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.8728. Min Act: -0.1700
Data Index: 3599304 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.8415. Min Act: -0.1700
Data Index: 35052 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.8571. Min Act: -0.1700
Data Index: 2629124 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7946. Min Act: -0.1700
Data Index: 6006378 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7790. Min Act: -0.1700
Data Index: 2945952 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7946. Min Act: -0.1700
Data Index: 8056593 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7633. Min Act: -0.1700
Data Index: 2407891 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7633. Min Act: -0.1700
Data Index: 5582112 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7320. Min Act: -0.1700
Data Index: 2662145 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7320. Min Act: -0.1700
Data Index: 7107405 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7320. Min Act: -0.1700
Data Index: 755702 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7164. Min Act: -0.1700
Data Index: 6279256 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7008. Min Act: -0.1700
Data Index: 8442819 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7008. Min Act: -0.1700
Data Index: 1388358 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.7008. Min Act: -0.1700
Data Index: 4904171 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.6695. Min Act: -0.1700
Data Index: 5562425 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.6695. Min Act: -0.1700
Data Index: 964401 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.6851. Min Act: -0.1700
Data Index: 5058173 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.6695. Min Act: -0.1700
Data Index: 7593146 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8728. Min Range: -3.8728
Max Act: 3.6382. Min Act: -0.1700
Data Index: 5699072 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19