Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5652 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2696. Min Range: -7.2696
Max Act: 7.2696. Min Act: -0.1700
Data Index: 5400497 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2696. Min Range: -7.2696
Max Act: 7.0821. Min Act: -0.1700
Data Index: 7573561 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2696. Min Range: -7.2696
Max Act: 7.0508. Min Act: -0.1700
Data Index: 3056563 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.9571. Min Act: -0.1700
Data Index: 2609506 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.9258. Min Act: -0.1700
Data Index: 2973502 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.8633. Min Act: -0.1700
Data Index: 7636730 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.8946. Min Act: -0.1700
Data Index: 4733417 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.8633. Min Act: -0.1700
Data Index: 4857944 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.8633. Min Act: -0.1700
Data Index: 5312309 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.8321. Min Act: -0.1700
Data Index: 7157143 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.8008. Min Act: -0.1700
Data Index: 8752838 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7696. Min Act: -0.1700
Data Index: 3527727 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7383. Min Act: -0.1700
Data Index: 1994977 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7383. Min Act: -0.1700
Data Index: 5987294 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7383. Min Act: -0.1700
Data Index: 7732748 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7383. Min Act: -0.1700
Data Index: 8809187 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7071. Min Act: -0.1700
Data Index: 211403 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7071. Min Act: -0.1700
Data Index: 3631129 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7071. Min Act: -0.1700
Data Index: 8549172 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2696. Min Range: -7.2696
Max Act: 6.7383. Min Act: -0.1700
Data Index: 72300 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19