Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.9305. Min Act: -0.1700
Data Index: 5877920 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.5867. Min Act: -0.1700
Data Index: 2518329 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.5555. Min Act: -0.1700
Data Index: 1321835 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.4930. Min Act: -0.1700
Data Index: 1617981 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.4617. Min Act: -0.1700
Data Index: 1218969 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.4305. Min Act: -0.1700
Data Index: 1654050 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.4617. Min Act: -0.1700
Data Index: 5650534 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.4305. Min Act: -0.1700
Data Index: 1319592 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.4305. Min Act: -0.1700
Data Index: 2051253 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.4305. Min Act: -0.1700
Data Index: 1663930 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3680. Min Act: -0.1700
Data Index: 6308885 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3992. Min Act: -0.1700
Data Index: 8375034 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3680. Min Act: -0.1700
Data Index: 380904 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3680. Min Act: -0.1700
Data Index: 7108724 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3680. Min Act: -0.1700
Data Index: 3409655 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3680. Min Act: -0.1700
Data Index: 1657179 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3680. Min Act: -0.1700
Data Index: 1730625 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3680. Min Act: -0.1700
Data Index: 3049328 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3367. Min Act: -0.1700
Data Index: 1786373 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9305. Min Range: -5.9305
Max Act: 5.3367. Min Act: -0.1700
Data Index: 1930200 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19