Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2461 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.7323. Min Act: -0.1700
Data Index: 8291666 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.7323. Min Act: -0.1700
Data Index: 4630932 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.6698. Min Act: -0.1700
Data Index: 4699448 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.6073. Min Act: -0.1700
Data Index: 5210281 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.5448. Min Act: -0.1700
Data Index: 4986187 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.4198. Min Act: -0.1700
Data Index: 3846385 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.4198. Min Act: -0.1700
Data Index: 4521425 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.4198. Min Act: -0.1700
Data Index: 7636217 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.2948. Min Act: -0.1700
Data Index: 8517003 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.2948. Min Act: -0.1700
Data Index: 6932539 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.2323. Min Act: -0.1700
Data Index: 8378202 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.2323. Min Act: -0.1700
Data Index: 7836985 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.2323. Min Act: -0.1700
Data Index: 924771 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.1073. Min Act: -0.1700
Data Index: 113022 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.1073. Min Act: -0.1700
Data Index: 2875837 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7323. Min Range: -10.7323
Max Act: 10.0448. Min Act: -0.1700
Data Index: 5622268 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7323. Min Range: -10.7323
Max Act: 9.9823. Min Act: -0.1700
Data Index: 7300108 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7323. Min Range: -10.7323
Max Act: 9.9823. Min Act: -0.1700
Data Index: 7116781 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7323. Min Range: -10.7323
Max Act: 9.9198. Min Act: -0.1700
Data Index: 8147552 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7323. Min Range: -10.7323
Max Act: 9.9198. Min Act: -0.1700
Data Index: 3038535 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19