Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 342 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.6463. Min Act: -0.1700
Data Index: 3775388 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.5838. Min Act: -0.1700
Data Index: 6788089 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.3963. Min Act: -0.1700
Data Index: 7109674 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.3963. Min Act: -0.1700
Data Index: 3941344 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.3338. Min Act: -0.1700
Data Index: 2752702 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.2713. Min Act: -0.1700
Data Index: 2602950 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.2713. Min Act: -0.1700
Data Index: 4807952 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.2088. Min Act: -0.1700
Data Index: 7322615 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.2088. Min Act: -0.1700
Data Index: 339073 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.1463. Min Act: -0.1700
Data Index: 2158825 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.1463. Min Act: -0.1700
Data Index: 3986893 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0838. Min Act: -0.1700
Data Index: 6900710 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0838. Min Act: -0.1700
Data Index: 5010999 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0838. Min Act: -0.1700
Data Index: 8281670 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0213. Min Act: -0.1700
Data Index: 2172293 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0213. Min Act: -0.1700
Data Index: 2965815 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0213. Min Act: -0.1700
Data Index: 5623984 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6463. Min Range: -9.6463
Max Act: 8.9588. Min Act: -0.1700
Data Index: 5520230 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0213. Min Act: -0.1700
Data Index: 3732628 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6463. Min Range: -9.6463
Max Act: 9.0213. Min Act: -0.1700
Data Index: 1839510 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19