Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3517 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.6494. Min Act: -0.1700
Data Index: 2603375 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.5869. Min Act: -0.1700
Data Index: 4343970 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.4619. Min Act: -0.1700
Data Index: 7731945 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.4619. Min Act: -0.1700
Data Index: 8044754 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.4931. Min Act: -0.1700
Data Index: 636253 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.4619. Min Act: -0.1700
Data Index: 756762 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.4306. Min Act: -0.1700
Data Index: 4994748 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3994. Min Act: -0.1700
Data Index: 875125 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3994. Min Act: -0.1700
Data Index: 7640854 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3994. Min Act: -0.1700
Data Index: 5444892 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3681. Min Act: -0.1700
Data Index: 8815485 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3369. Min Act: -0.1700
Data Index: 5566083 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3681. Min Act: -0.1700
Data Index: 6900631 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3056. Min Act: -0.1700
Data Index: 5272946 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.3056. Min Act: -0.1700
Data Index: 7117286 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.2744. Min Act: -0.1700
Data Index: 4497632 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.2744. Min Act: -0.1700
Data Index: 3918123 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.2744. Min Act: -0.1700
Data Index: 8133519 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.2744. Min Act: -0.1700
Data Index: 978572 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6494. Min Range: -4.6494
Max Act: 4.2431. Min Act: -0.1700
Data Index: 2150407 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19