Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6357 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4257. Min Range: -6.4257
Max Act: 6.4257. Min Act: -0.1700
Data Index: 6833829 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.9569. Min Act: -0.1700
Data Index: 4768012 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8944. Min Act: -0.1700
Data Index: 4168385 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8632. Min Act: -0.1700
Data Index: 759676 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8632. Min Act: -0.1700
Data Index: 7660849 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.8007. Min Act: -0.1700
Data Index: 886809 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.7694. Min Act: -0.1700
Data Index: 5931542 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.7694. Min Act: -0.1700
Data Index: 2353175 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.7382. Min Act: -0.1700
Data Index: 7847116 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.7382. Min Act: -0.1700
Data Index: 233635 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.7069. Min Act: -0.1700
Data Index: 2042726 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.6757. Min Act: -0.1700
Data Index: 5427971 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.6757. Min Act: -0.1700
Data Index: 4553131 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.6444. Min Act: -0.1700
Data Index: 7718050 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.6444. Min Act: -0.1700
Data Index: 2980498 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.5819. Min Act: -0.1700
Data Index: 6337741 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.5819. Min Act: -0.1700
Data Index: 4298337 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.5194. Min Act: -0.1700
Data Index: 1438837 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.5194. Min Act: -0.1700
Data Index: 4418001 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4257. Min Range: -6.4257
Max Act: 5.4882. Min Act: -0.1700
Data Index: 369784 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19