Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0444. Min Range: -4.0444
Max Act: 4.0444. Min Act: -0.1700
Data Index: 837507 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.9819. Min Act: -0.1700
Data Index: 5584853 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.9819. Min Act: -0.1700
Data Index: 7428405 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.9507. Min Act: -0.1700
Data Index: 8183745 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.9194. Min Act: -0.1700
Data Index: 949130 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.9194. Min Act: -0.1700
Data Index: 7136510 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8881. Min Act: -0.1700
Data Index: 2209344 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8881. Min Act: -0.1700
Data Index: 4230499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8881. Min Act: -0.1700
Data Index: 689158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 8698887 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8881. Min Act: -0.1700
Data Index: 2741909 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8881. Min Act: -0.1700
Data Index: 6382221 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 2998143 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 6633247 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 3482778 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 7506164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 365079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 5941243 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 4554005 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0444. Min Range: -4.0444
Max Act: 3.8569. Min Act: -0.1700
Data Index: 2478982 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19