Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4855. Min Range: -9.4855
Max Act: 9.4855. Min Act: -0.1700
Data Index: 4945311 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4855. Min Range: -9.4855
Max Act: 9.4855. Min Act: -0.1700
Data Index: 4021475 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4855. Min Range: -9.4855
Max Act: 9.4230. Min Act: -0.1700
Data Index: 2485596 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4855. Min Range: -9.4855
Max Act: 9.3605. Min Act: -0.1700
Data Index: 2802775 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4855. Min Range: -9.4855
Max Act: 9.2355. Min Act: -0.1700
Data Index: 2029295 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4855. Min Range: -9.4855
Max Act: 9.1105. Min Act: -0.1700
Data Index: 1304196 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.9230. Min Act: -0.1700
Data Index: 8499632 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.8605. Min Act: -0.1700
Data Index: 6767163 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.7980. Min Act: -0.1700
Data Index: 5115675 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.7355. Min Act: -0.1700
Data Index: 8485723 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.7355. Min Act: -0.1700
Data Index: 6911056 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.6730. Min Act: -0.1700
Data Index: 6432481 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.6730. Min Act: -0.1700
Data Index: 6148070 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.6105. Min Act: -0.1700
Data Index: 8326182 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.6105. Min Act: -0.1700
Data Index: 893766 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.6105. Min Act: -0.1700
Data Index: 7546690 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.6105. Min Act: -0.1700
Data Index: 5563639 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.5480. Min Act: -0.1700
Data Index: 8111981 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.5480. Min Act: -0.1700
Data Index: 4846623 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4855. Min Range: -9.4855
Max Act: 8.5480. Min Act: -0.1700
Data Index: 1433778 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19