Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5430 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.8944. Min Act: -0.1700
Data Index: 4115680 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.8319. Min Act: -0.1700
Data Index: 630146 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.7069. Min Act: -0.1700
Data Index: 3381189 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6444. Min Act: -0.1700
Data Index: 574416 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6757. Min Act: -0.1700
Data Index: 3817321 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.7069. Min Act: -0.1700
Data Index: 1581452 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6444. Min Act: -0.1700
Data Index: 5586326 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6132. Min Act: -0.1700
Data Index: 1703304 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6444. Min Act: -0.1700
Data Index: 3549424 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6444. Min Act: -0.1700
Data Index: 1815470 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6132. Min Act: -0.1700
Data Index: 5240790 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6132. Min Act: -0.1700
Data Index: 1110748 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.5819. Min Act: -0.1700
Data Index: 6275801 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6444. Min Act: -0.1700
Data Index: 172931 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6132. Min Act: -0.1700
Data Index: 109099 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.6132. Min Act: -0.1700
Data Index: 1616825 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.5819. Min Act: -0.1700
Data Index: 5022885 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.5819. Min Act: -0.1700
Data Index: 2916087 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.5819. Min Act: -0.1700
Data Index: 5751277 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8944. Min Range: -6.8944
Max Act: 6.5507. Min Act: -0.1700
Data Index: 3520888 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19