Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1132 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.9526. Min Act: -0.1700
Data Index: 3539208 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.7651. Min Act: -0.1700
Data Index: 84681 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.7026. Min Act: -0.1700
Data Index: 534715 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.5463. Min Act: -0.1700
Data Index: 8038756 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.4526. Min Act: -0.1700
Data Index: 8182151 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.4526. Min Act: -0.1700
Data Index: 5166430 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.3901. Min Act: -0.1700
Data Index: 2071033 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.3588. Min Act: -0.1700
Data Index: 1673120 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.3588. Min Act: -0.1700
Data Index: 1900264 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.3276. Min Act: -0.1700
Data Index: 904632 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.2651. Min Act: -0.1700
Data Index: 5706777 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.2338. Min Act: -0.1700
Data Index: 3812938 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.2651. Min Act: -0.1700
Data Index: 7501654 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.2338. Min Act: -0.1700
Data Index: 8462836 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.2338. Min Act: -0.1700
Data Index: 3848679 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.1713. Min Act: -0.1700
Data Index: 1984436 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.1401. Min Act: -0.1700
Data Index: 4881456 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.1401. Min Act: -0.1700
Data Index: 1416684 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.1088. Min Act: -0.1700
Data Index: 6200568 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9526. Min Range: -6.9526
Max Act: 6.0776. Min Act: -0.1700
Data Index: 4559878 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19