Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2597 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.6026. Min Act: -0.1700
Data Index: 7919739 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.5713. Min Act: -0.1700
Data Index: 6410596 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.5400. Min Act: -0.1700
Data Index: 7786574 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.5400. Min Act: -0.1700
Data Index: 5706728 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.5087. Min Act: -0.1700
Data Index: 3457007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.5087. Min Act: -0.1700
Data Index: 3617320 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.5087. Min Act: -0.1700
Data Index: 6322854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4460. Min Act: -0.1700
Data Index: 2847216 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4460. Min Act: -0.1700
Data Index: 3309322 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4460. Min Act: -0.1700
Data Index: 4824425 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4460. Min Act: -0.1700
Data Index: 7659842 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.3833. Min Act: -0.1700
Data Index: 3935740 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 4492791 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 4725714 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 4978794 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 987016 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 5605175 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 5651241 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 6166705 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6026. Min Range: -3.6026
Max Act: 3.4147. Min Act: -0.1700
Data Index: 1598127 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19