Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 697 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.3066. Min Act: -0.1700
Data Index: 106151 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.3066. Min Act: -0.1700
Data Index: 4093777 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2406. Min Act: -0.1700
Data Index: 363436 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2241. Min Act: -0.1700
Data Index: 570707 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2406. Min Act: -0.1700
Data Index: 6784810 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2241. Min Act: -0.1700
Data Index: 237994 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.2406. Min Act: -0.1700
Data Index: 6528282 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 5211576 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 3828796 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 1037575 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 1625307 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1909. Min Act: -0.1700
Data Index: 3474173 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 8712526 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 3199871 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 6594037 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1410. Min Act: -0.1700
Data Index: 6778690 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1577. Min Act: -0.1700
Data Index: 1535417 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1743. Min Act: -0.1700
Data Index: 6101856 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1577. Min Act: -0.1700
Data Index: 1203079 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3066. Min Range: -2.3066
Max Act: 2.1577. Min Act: -0.1700
Data Index: 5943156 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19