Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.2465. Min Act: -0.1700
Data Index: 5989036 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1840. Min Act: -0.1700
Data Index: 6758268 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1840. Min Act: -0.1700
Data Index: 1500922 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.1527. Min Act: -0.1700
Data Index: 1420214 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0902. Min Act: -0.1700
Data Index: 7772246 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2465. Min Range: -5.2465
Max Act: 5.0277. Min Act: -0.1700
Data Index: 2875216 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9965. Min Act: -0.1700
Data Index: 704550 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9965. Min Act: -0.1700
Data Index: 4177571 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9652. Min Act: -0.1700
Data Index: 477849 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9652. Min Act: -0.1700
Data Index: 3951810 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9652. Min Act: -0.1700
Data Index: 2426772 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9340. Min Act: -0.1700
Data Index: 1294595 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9652. Min Act: -0.1700
Data Index: 7727113 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9652. Min Act: -0.1700
Data Index: 1151247 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9340. Min Act: -0.1700
Data Index: 7239453 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9652. Min Act: -0.1700
Data Index: 7288091 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9027. Min Act: -0.1700
Data Index: 4583530 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9027. Min Act: -0.1700
Data Index: 364155 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.9027. Min Act: -0.1700
Data Index: 7164964 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2465. Min Range: -5.2465
Max Act: 4.8715. Min Act: -0.1700
Data Index: 4023055 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19