Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.5214. Min Act: -0.1700
Data Index: 7551055 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4901. Min Act: -0.1700
Data Index: 5048716 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4901. Min Act: -0.1700
Data Index: 8373389 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4589. Min Act: -0.1700
Data Index: 1673719 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4276. Min Act: -0.1700
Data Index: 6209345 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4276. Min Act: -0.1700
Data Index: 3965610 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4276. Min Act: -0.1700
Data Index: 3777365 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.4276. Min Act: -0.1700
Data Index: 1320545 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3964. Min Act: -0.1700
Data Index: 3637261 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3964. Min Act: -0.1700
Data Index: 6996559 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3651. Min Act: -0.1700
Data Index: 7132446 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 6902259 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3651. Min Act: -0.1700
Data Index: 1847960 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3964. Min Act: -0.1700
Data Index: 332097 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 129858 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 690196 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 3192533 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 3338488 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 4424969 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5214. Min Range: -5.5214
Max Act: 5.3339. Min Act: -0.1700
Data Index: 2805480 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19