Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.4646. Min Act: -0.1700
Data Index: 3034241 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.4646. Min Act: -0.1700
Data Index: 5855340 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.4021. Min Act: -0.1700
Data Index: 4871749 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.4021. Min Act: -0.1700
Data Index: 827569 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.3396. Min Act: -0.1700
Data Index: 4818326 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.3396. Min Act: -0.1700
Data Index: 339240 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.2771. Min Act: -0.1700
Data Index: 4132071 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.3396. Min Act: -0.1700
Data Index: 4779428 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.2771. Min Act: -0.1700
Data Index: 15004 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.1521. Min Act: -0.1700
Data Index: 4496808 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9646. Min Act: -0.1700
Data Index: 3848017 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.0271. Min Act: -0.1700
Data Index: 1717243 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4646. Min Range: -8.4646
Max Act: 8.0271. Min Act: -0.1700
Data Index: 4412604 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9646. Min Act: -0.1700
Data Index: 1480125 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9646. Min Act: -0.1700
Data Index: 3145146 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9646. Min Act: -0.1700
Data Index: 6818913 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9646. Min Act: -0.1700
Data Index: 7029537 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9021. Min Act: -0.1700
Data Index: 5713343 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9021. Min Act: -0.1700
Data Index: 1405022 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4646. Min Range: -8.4646
Max Act: 7.9021. Min Act: -0.1700
Data Index: 2270702 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19