Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.6457. Min Act: -0.1700
Data Index: 478134 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 3293720 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.6144. Min Act: -0.1700
Data Index: 7995838 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 7544103 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 3662635 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 78536 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 7036615 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 7612491 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5832. Min Act: -0.1700
Data Index: 1094813 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5519. Min Act: -0.1700
Data Index: 843525 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5207. Min Act: -0.1700
Data Index: 287786 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5207. Min Act: -0.1700
Data Index: 3394846 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4894. Min Act: -0.1700
Data Index: 302792 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.5519. Min Act: -0.1700
Data Index: 3390668 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4894. Min Act: -0.1700
Data Index: 2114062 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4894. Min Act: -0.1700
Data Index: 2278012 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4894. Min Act: -0.1700
Data Index: 554040 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4894. Min Act: -0.1700
Data Index: 929531 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4894. Min Act: -0.1700
Data Index: 7776510 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6457. Min Range: -4.6457
Max Act: 4.4582. Min Act: -0.1699
Data Index: 923357 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19