Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2670 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2437. Min Range: -5.2437
Max Act: 5.2437. Min Act: -0.1700
Data Index: 2504153 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2437. Min Range: -5.2437
Max Act: 5.1187. Min Act: -0.1700
Data Index: 1848715 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2437. Min Range: -5.2437
Max Act: 5.0562. Min Act: -0.1700
Data Index: 4739687 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9937. Min Act: -0.1700
Data Index: 1343716 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9625. Min Act: -0.1700
Data Index: 7471697 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9625. Min Act: -0.1700
Data Index: 6437406 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9625. Min Act: -0.1700
Data Index: 1251409 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 8083428 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9000. Min Act: -0.1700
Data Index: 1343736 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 8516497 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 1343713 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 4188250 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 4722984 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 2119278 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 3969763 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 7642551 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9625. Min Act: -0.1700
Data Index: 4722978 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9312. Min Act: -0.1700
Data Index: 4722977 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.8687. Min Act: -0.1700
Data Index: 4089550 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2437. Min Range: -5.2437
Max Act: 4.9000. Min Act: -0.1700
Data Index: 6771920 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19