Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4852 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.5713. Min Act: -0.1700
Data Index: 8499338 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.4775. Min Act: -0.1700
Data Index: 7877497 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.4775. Min Act: -0.1700
Data Index: 3763499 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.3838. Min Act: -0.1700
Data Index: 8411985 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.3525. Min Act: -0.1700
Data Index: 1077070 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.3838. Min Act: -0.1700
Data Index: 1788024 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.3838. Min Act: -0.1700
Data Index: 1288092 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.3525. Min Act: -0.1700
Data Index: 5807857 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.3213. Min Act: -0.1700
Data Index: 417958 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.3213. Min Act: -0.1700
Data Index: 4015150 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2900. Min Act: -0.1700
Data Index: 176050 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2900. Min Act: -0.1700
Data Index: 7620463 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2588. Min Act: -0.1700
Data Index: 458896 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2588. Min Act: -0.1700
Data Index: 6690484 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2588. Min Act: -0.1700
Data Index: 1490793 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2588. Min Act: -0.1700
Data Index: 1193109 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2588. Min Act: -0.1700
Data Index: 8831469 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2588. Min Act: -0.1700
Data Index: 8167710 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2588. Min Act: -0.1700
Data Index: 968588 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5713. Min Range: -5.5713
Max Act: 5.2275. Min Act: -0.1700
Data Index: 3339872 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19