Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1497 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.3162. Min Act: -0.1700
Data Index: 2909180 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2848. Min Act: -0.1700
Data Index: 4987791 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2534. Min Act: -0.1700
Data Index: 1151588 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2691. Min Act: -0.1700
Data Index: 2810018 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2377. Min Act: -0.1700
Data Index: 4728013 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2220. Min Act: -0.1700
Data Index: 2802898 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2377. Min Act: -0.1700
Data Index: 3836544 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2534. Min Act: -0.1700
Data Index: 7249754 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2377. Min Act: -0.1700
Data Index: 7702749 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2063. Min Act: -0.1700
Data Index: 570786 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2220. Min Act: -0.1700
Data Index: 6077498 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1906. Min Act: -0.1700
Data Index: 8685830 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2063. Min Act: -0.1700
Data Index: 8142865 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1906. Min Act: -0.1700
Data Index: 5030046 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2063. Min Act: -0.1700
Data Index: 3124040 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1906. Min Act: -0.1700
Data Index: 2722292 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2063. Min Act: -0.1700
Data Index: 5457922 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.2063. Min Act: -0.1700
Data Index: 798001 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1748. Min Act: -0.1700
Data Index: 7760995 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3162. Min Range: -3.3162
Max Act: 3.1748. Min Act: -0.1700
Data Index: 8271259 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19