Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2064 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.4911. Min Act: -0.1700
Data Index: 7184509 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.3349. Min Act: -0.1700
Data Index: 975212 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.3349. Min Act: -0.1700
Data Index: 1217882 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.3036. Min Act: -0.1700
Data Index: 4879179 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.2724. Min Act: -0.1700
Data Index: 3637403 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.1161. Min Act: -0.1700
Data Index: 6411126 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.0849. Min Act: -0.1700
Data Index: 2301246 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.1161. Min Act: -0.1700
Data Index: 8033510 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.0849. Min Act: -0.1700
Data Index: 539055 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.0224. Min Act: -0.1700
Data Index: 4342019 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4911. Min Range: -5.4911
Max Act: 5.0224. Min Act: -0.1700
Data Index: 4708712 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.9911. Min Act: -0.1700
Data Index: 2259290 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.9286. Min Act: -0.1700
Data Index: 46239 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.9286. Min Act: -0.1700
Data Index: 648740 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.8974. Min Act: -0.1700
Data Index: 246416 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.8974. Min Act: -0.1700
Data Index: 2734558 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.8974. Min Act: -0.1700
Data Index: 3071680 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.8974. Min Act: -0.1700
Data Index: 6038794 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.8974. Min Act: -0.1700
Data Index: 7117048 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4911. Min Range: -5.4911
Max Act: 4.8974. Min Act: -0.1700
Data Index: 4917587 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19