Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3539 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.9426. Min Act: -0.1700
Data Index: 3584165 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.9426. Min Act: -0.1700
Data Index: 4042685 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.9114. Min Act: -0.1700
Data Index: 7028359 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.8801. Min Act: -0.1700
Data Index: 257802 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.8801. Min Act: -0.1700
Data Index: 8347805 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.8489. Min Act: -0.1700
Data Index: 1771094 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.8489. Min Act: -0.1700
Data Index: 4950837 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.8176. Min Act: -0.1700
Data Index: 1610604 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.8176. Min Act: -0.1700
Data Index: 5350343 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7551. Min Act: -0.1700
Data Index: 2843938 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7551. Min Act: -0.1700
Data Index: 5768876 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7239. Min Act: -0.1700
Data Index: 1177486 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7551. Min Act: -0.1700
Data Index: 4890365 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7239. Min Act: -0.1700
Data Index: 2443741 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7239. Min Act: -0.1700
Data Index: 8275253 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7239. Min Act: -0.1700
Data Index: 2706638 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7239. Min Act: -0.1700
Data Index: 5706511 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7239. Min Act: -0.1700
Data Index: 5841941 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.7239. Min Act: -0.1700
Data Index: 1744804 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9426. Min Range: -4.9426
Max Act: 4.6926. Min Act: -0.1700
Data Index: 3030242 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19