Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3256 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.4700. Min Act: -0.1700
Data Index: 3630299 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.4388. Min Act: -0.1700
Data Index: 5122296 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2825. Min Act: -0.1700
Data Index: 968294 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2825. Min Act: -0.1700
Data Index: 7229559 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2825. Min Act: -0.1700
Data Index: 4860909 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2513. Min Act: -0.1700
Data Index: 6214303 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2825. Min Act: -0.1700
Data Index: 3067271 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2825. Min Act: -0.1700
Data Index: 4092943 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2200. Min Act: -0.1700
Data Index: 2299847 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2200. Min Act: -0.1700
Data Index: 6213183 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.1888. Min Act: -0.1700
Data Index: 8168044 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2200. Min Act: -0.1700
Data Index: 6214302 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2200. Min Act: -0.1700
Data Index: 7889067 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.2200. Min Act: -0.1700
Data Index: 5122294 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.1888. Min Act: -0.1700
Data Index: 4035971 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.1888. Min Act: -0.1700
Data Index: 2597882 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.1888. Min Act: -0.1700
Data Index: 5122295 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.1575. Min Act: -0.1700
Data Index: 6488408 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.1575. Min Act: -0.1700
Data Index: 6533595 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4700. Min Range: -5.4700
Max Act: 5.1575. Min Act: -0.1700
Data Index: 5868705 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19