Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.3938. Min Act: -0.1700
Data Index: 3672716 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.3938. Min Act: -0.1700
Data Index: 8023497 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.2375. Min Act: -0.1700
Data Index: 2873065 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1438. Min Act: -0.1700
Data Index: 1949095 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1438. Min Act: -0.1700
Data Index: 8356668 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1125. Min Act: -0.1700
Data Index: 4620602 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1438. Min Act: -0.1700
Data Index: 2971764 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1438. Min Act: -0.1700
Data Index: 7718549 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1438. Min Act: -0.1700
Data Index: 1720449 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1125. Min Act: -0.1700
Data Index: 8227344 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1438. Min Act: -0.1700
Data Index: 3736039 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1125. Min Act: -0.1700
Data Index: 8284552 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.0813. Min Act: -0.1700
Data Index: 2881834 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.0813. Min Act: -0.1700
Data Index: 6336915 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.1125. Min Act: -0.1700
Data Index: 7461962 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.0188. Min Act: -0.1700
Data Index: 179868 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.0188. Min Act: -0.1700
Data Index: 2066032 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.0500. Min Act: -0.1700
Data Index: 2468157 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.0813. Min Act: -0.1700
Data Index: 5870618 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3938. Min Range: -7.3938
Max Act: 7.0500. Min Act: -0.1700
Data Index: 3524071 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #19