Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3307 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.5790. Min Act: -0.1700
Data Index: 8296452 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.5477. Min Act: -0.1700
Data Index: 5446322 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.5790. Min Act: -0.1700
Data Index: 3320618 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.5790. Min Act: -0.1700
Data Index: 5747836 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.5477. Min Act: -0.1700
Data Index: 4880754 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.4852. Min Act: -0.1700
Data Index: 7520893 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.4852. Min Act: -0.1700
Data Index: 3862601 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.4852. Min Act: -0.1700
Data Index: 6236394 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.4227. Min Act: -0.1700
Data Index: 5398762 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.4227. Min Act: -0.1700
Data Index: 8627172 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.4540. Min Act: -0.1700
Data Index: 6641423 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.3915. Min Act: -0.1700
Data Index: 1597078 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.3915. Min Act: -0.1700
Data Index: 355676 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.3602. Min Act: -0.1700
Data Index: 471621 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.3602. Min Act: -0.1700
Data Index: 5025857 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.3290. Min Act: -0.1700
Data Index: 549102 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.3290. Min Act: -0.1700
Data Index: 1916549 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.2977. Min Act: -0.1700
Data Index: 5234338 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.2352. Min Act: -0.1700
Data Index: 3033338 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5790. Min Range: -5.5790
Max Act: 5.2665. Min Act: -0.1700
Data Index: 7717900 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19