Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2964 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.9444. Min Act: -0.1700
Data Index: 388319 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.8194. Min Act: -0.1700
Data Index: 958551 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.2881. Min Act: -0.1700
Data Index: 4326228 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.2256. Min Act: -0.1700
Data Index: 7201702 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.2256. Min Act: -0.1700
Data Index: 1804847 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.1944. Min Act: -0.1700
Data Index: 7124852 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.1006. Min Act: -0.1700
Data Index: 5757800 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.1631. Min Act: -0.1700
Data Index: 1762542 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.0381. Min Act: -0.1700
Data Index: 6249594 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.0381. Min Act: -0.1700
Data Index: 3908875 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.0381. Min Act: -0.1700
Data Index: 8401567 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.0069. Min Act: -0.1700
Data Index: 2549026 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9444. Min Range: -7.9444
Max Act: 7.0069. Min Act: -0.1700
Data Index: 4187023 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9444. Min Range: -7.9444
Max Act: 6.9756. Min Act: -0.1700
Data Index: 6487023 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9444. Min Range: -7.9444
Max Act: 6.9756. Min Act: -0.1700
Data Index: 7953633 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9444. Min Range: -7.9444
Max Act: 6.8819. Min Act: -0.1700
Data Index: 3107456 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9444. Min Range: -7.9444
Max Act: 6.8819. Min Act: -0.1700
Data Index: 6242613 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9444. Min Range: -7.9444
Max Act: 6.8819. Min Act: -0.1700
Data Index: 8103701 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9444. Min Range: -7.9444
Max Act: 6.8506. Min Act: -0.1700
Data Index: 6123729 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9444. Min Range: -7.9444
Max Act: 6.8506. Min Act: -0.1700
Data Index: 7928903 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19