Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 605 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.2572. Min Act: -0.1700
Data Index: 2825266 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1947. Min Act: -0.1700
Data Index: 1877715 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1947. Min Act: -0.1700
Data Index: 6039532 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1634. Min Act: -0.1700
Data Index: 8156198 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1634. Min Act: -0.1700
Data Index: 3899283 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1009. Min Act: -0.1700
Data Index: 5657681 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1009. Min Act: -0.1700
Data Index: 5165461 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1009. Min Act: -0.1700
Data Index: 8484525 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1009. Min Act: -0.1700
Data Index: 6526988 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0697. Min Act: -0.1700
Data Index: 1776810 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.1009. Min Act: -0.1700
Data Index: 752123 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0697. Min Act: -0.1700
Data Index: 3899282 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0697. Min Act: -0.1700
Data Index: 8401786 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 7049650 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 668224 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0072. Min Act: -0.1700
Data Index: 2355254 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 7527759 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0384. Min Act: -0.1700
Data Index: 4024420 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2572. Min Range: -5.2572
Max Act: 5.0072. Min Act: -0.1700
Data Index: 6789061 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2572. Min Range: -5.2572
Max Act: 4.9759. Min Act: -0.1700
Data Index: 2766700 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19