Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4491 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.7946. Min Act: -0.1700
Data Index: 988492 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.7321. Min Act: -0.1700
Data Index: 5404978 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.7009. Min Act: -0.1700
Data Index: 1581403 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.6696. Min Act: -0.1700
Data Index: 6531181 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.7009. Min Act: -0.1700
Data Index: 5615250 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.6696. Min Act: -0.1700
Data Index: 8445536 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.6384. Min Act: -0.1700
Data Index: 6665602 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.6384. Min Act: -0.1700
Data Index: 549370 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.6071. Min Act: -0.1700
Data Index: 5375534 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.5446. Min Act: -0.1700
Data Index: 556309 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.5446. Min Act: -0.1700
Data Index: 4465626 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.5446. Min Act: -0.1700
Data Index: 4443979 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.5446. Min Act: -0.1700
Data Index: 4743572 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.5446. Min Act: -0.1700
Data Index: 3979314 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.5134. Min Act: -0.1700
Data Index: 6891174 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.4821. Min Act: -0.1700
Data Index: 403108 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.4821. Min Act: -0.1700
Data Index: 6823764 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.4196. Min Act: -0.1700
Data Index: 2723041 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.4509. Min Act: -0.1700
Data Index: 5541654 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7946. Min Range: -5.7946
Max Act: 5.4509. Min Act: -0.1700
Data Index: 8497740 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19