Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.9844. Min Act: -0.1700
Data Index: 8664052 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.9531. Min Act: -0.1700
Data Index: 5655135 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.9531. Min Act: -0.1700
Data Index: 1680451 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.9219. Min Act: -0.1700
Data Index: 1377707 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.9219. Min Act: -0.1700
Data Index: 3838631 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.9219. Min Act: -0.1700
Data Index: 7683109 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 4378440 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 4104169 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 8106470 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 1611306 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 2579260 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 6862468 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 1593479 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 2366738 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 1019646 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 6815494 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 6761041 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8906. Min Act: -0.1700
Data Index: 4208166 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8593. Min Act: -0.1700
Data Index: 1727871 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9844. Min Range: -3.9844
Max Act: 3.8593. Min Act: -0.1700
Data Index: 1823331 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19