Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2863 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.7524. Min Act: -0.1700
Data Index: 7055132 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.6899. Min Act: -0.1700
Data Index: 7029099 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.5961. Min Act: -0.1700
Data Index: 2440502 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.5649. Min Act: -0.1700
Data Index: 1950720 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.5024. Min Act: -0.1700
Data Index: 8229455 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.4711. Min Act: -0.1700
Data Index: 5779961 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.4399. Min Act: -0.1700
Data Index: 7722758 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.4086. Min Act: -0.1700
Data Index: 7509835 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.4086. Min Act: -0.1700
Data Index: 3470906 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.3774. Min Act: -0.1700
Data Index: 180774 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.3461. Min Act: -0.1700
Data Index: 8762411 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.2836. Min Act: -0.1700
Data Index: 358016 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.2211. Min Act: -0.1700
Data Index: 2513662 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.1899. Min Act: -0.1700
Data Index: 6091203 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.1899. Min Act: -0.1700
Data Index: 5286744 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.1899. Min Act: -0.1700
Data Index: 5364434 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.1586. Min Act: -0.1700
Data Index: 7139553 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.1586. Min Act: -0.1700
Data Index: 3497713 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.1586. Min Act: -0.1700
Data Index: 3484612 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7524. Min Range: -6.7524
Max Act: 6.1586. Min Act: -0.1700
Data Index: 1102897 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19