Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1736 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2548. Min Range: -4.2548
Max Act: 4.2548. Min Act: -0.1700
Data Index: 8505142 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2548. Min Range: -4.2548
Max Act: 4.0673. Min Act: -0.1700
Data Index: 13363 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2548. Min Range: -4.2548
Max Act: 4.0360. Min Act: -0.1700
Data Index: 8600154 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.8484. Min Act: -0.1700
Data Index: 3696830 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.8172. Min Act: -0.1700
Data Index: 2581110 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.8484. Min Act: -0.1700
Data Index: 2973878 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.8484. Min Act: -0.1700
Data Index: 6488769 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.8484. Min Act: -0.1700
Data Index: 2472070 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.8484. Min Act: -0.1700
Data Index: 2486605 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7859. Min Act: -0.1700
Data Index: 4972439 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.8172. Min Act: -0.1700
Data Index: 3354699 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7546. Min Act: -0.1700
Data Index: 302648 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7859. Min Act: -0.1700
Data Index: 7520005 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7859. Min Act: -0.1700
Data Index: 5089958 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7859. Min Act: -0.1700
Data Index: 454913 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7859. Min Act: -0.1700
Data Index: 3851313 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7546. Min Act: -0.1700
Data Index: 694371 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7546. Min Act: -0.1700
Data Index: 7059981 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7546. Min Act: -0.1700
Data Index: 257039 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2548. Min Range: -4.2548
Max Act: 3.7546. Min Act: -0.1700
Data Index: 3838586 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19