Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6394 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.7330. Min Act: -0.1700
Data Index: 4993196 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.5142. Min Act: -0.1697
Data Index: 6058502 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.4517. Min Act: -0.1696
Data Index: 7185606 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.4205. Min Act: -0.1700
Data Index: 4942007 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.4205. Min Act: -0.1666
Data Index: 6118324 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.3580. Min Act: -0.1700
Data Index: 2855358 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.2955. Min Act: -0.1700
Data Index: 2840175 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.2955. Min Act: -0.1700
Data Index: 7455704 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.2955. Min Act: -0.1700
Data Index: 997445 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.2955. Min Act: -0.1699
Data Index: 446187 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.2330. Min Act: -0.1700
Data Index: 7016665 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.2330. Min Act: -0.1698
Data Index: 5696686 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.1705. Min Act: -0.1700
Data Index: 1292766 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.1705. Min Act: -0.1700
Data Index: 3940717 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.1392. Min Act: -0.1700
Data Index: 6988544 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.0767. Min Act: -0.1700
Data Index: 3101964 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.0767. Min Act: -0.1699
Data Index: 1646383 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.0767. Min Act: -0.1699
Data Index: 1086235 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.0455. Min Act: -0.1689
Data Index: 1882692 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7330. Min Range: -7.7330
Max Act: 7.0767. Min Act: -0.1700
Data Index: 1890081 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19