Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.9422. Min Act: -0.1700
Data Index: 3924577 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.8484. Min Act: -0.1700
Data Index: 3924576 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.8484. Min Act: -0.1700
Data Index: 3131994 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.8172. Min Act: -0.1700
Data Index: 31606 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.7546. Min Act: -0.1700
Data Index: 9585 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.7233. Min Act: -0.1700
Data Index: 5430635 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.7546. Min Act: -0.1700
Data Index: 7987175 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.7233. Min Act: -0.1700
Data Index: 1494967 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6921. Min Act: -0.1700
Data Index: 933718 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6921. Min Act: -0.1700
Data Index: 193041 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6921. Min Act: -0.1700
Data Index: 6093290 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.7233. Min Act: -0.1700
Data Index: 3499317 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6608. Min Act: -0.1700
Data Index: 5839488 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6921. Min Act: -0.1700
Data Index: 6030210 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6608. Min Act: -0.1700
Data Index: 1316198 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6608. Min Act: -0.1700
Data Index: 4765958 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6608. Min Act: -0.1700
Data Index: 6023486 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6295. Min Act: -0.1700
Data Index: 2104828 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6608. Min Act: -0.1700
Data Index: 4338670 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9422. Min Range: -3.9422
Max Act: 3.6295. Min Act: -0.1700
Data Index: 666953 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19