Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3931 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.6571. Min Act: -0.1700
Data Index: 3779744 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.6258. Min Act: -0.1700
Data Index: 4278128 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.5946. Min Act: -0.1700
Data Index: 3826639 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.5946. Min Act: -0.1700
Data Index: 2586254 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.5633. Min Act: -0.1700
Data Index: 564824 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.5633. Min Act: -0.1700
Data Index: 366381 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.5633. Min Act: -0.1700
Data Index: 8670705 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.5321. Min Act: -0.1700
Data Index: 5362590 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.5008. Min Act: -0.1700
Data Index: 7033458 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.4383. Min Act: -0.1700
Data Index: 6323704 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.4071. Min Act: -0.1700
Data Index: 6219608 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.4071. Min Act: -0.1700
Data Index: 4908175 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.3758. Min Act: -0.1700
Data Index: 4860397 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.4071. Min Act: -0.1700
Data Index: 5213522 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.3758. Min Act: -0.1700
Data Index: 4860408 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.3446. Min Act: -0.1700
Data Index: 4860413 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.3758. Min Act: -0.1700
Data Index: 7488797 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.3758. Min Act: -0.1700
Data Index: 1859506 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.3758. Min Act: -0.1700
Data Index: 6803377 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6571. Min Range: -4.6571
Max Act: 4.3758. Min Act: -0.1700
Data Index: 838733 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19