Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 750 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.7859. Min Act: -0.1700
Data Index: 3069952 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.5981. Min Act: -0.1700
Data Index: 845566 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.5512. Min Act: -0.1700
Data Index: 3989850 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.4729. Min Act: -0.1700
Data Index: 6232709 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.4259. Min Act: -0.1700
Data Index: 7336956 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.4415. Min Act: -0.1700
Data Index: 928119 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.4102. Min Act: -0.1700
Data Index: 5279517 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3945. Min Act: -0.1700
Data Index: 6268421 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3631. Min Act: -0.1700
Data Index: 2924949 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3475. Min Act: -0.1700
Data Index: 4323661 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3475. Min Act: -0.1700
Data Index: 5923693 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3161. Min Act: -0.1700
Data Index: 1667632 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3004. Min Act: -0.1700
Data Index: 6983732 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3004. Min Act: -0.1700
Data Index: 6721135 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3004. Min Act: -0.1700
Data Index: 7991633 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.3004. Min Act: -0.1700
Data Index: 1207604 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.2847. Min Act: -0.1700
Data Index: 5853065 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.2690. Min Act: -0.1700
Data Index: 4053844 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.2690. Min Act: -0.1700
Data Index: 6677778 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7859. Min Range: -3.7859
Max Act: 3.2690. Min Act: -0.1700
Data Index: 1278321 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19