Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2930 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.9021. Min Act: -0.1700
Data Index: 8620389 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.8083. Min Act: -0.1700
Data Index: 2573099 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.8083. Min Act: -0.1700
Data Index: 2256663 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.8083. Min Act: -0.1700
Data Index: 1355837 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.7146. Min Act: -0.1700
Data Index: 149990 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.6833. Min Act: -0.1700
Data Index: 4510671 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.6521. Min Act: -0.1700
Data Index: 6069150 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.6521. Min Act: -0.1700
Data Index: 1219345 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.6521. Min Act: -0.1700
Data Index: 6026780 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.6208. Min Act: -0.1700
Data Index: 8663767 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.6208. Min Act: -0.1700
Data Index: 5035253 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.5896. Min Act: -0.1700
Data Index: 5082399 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.5896. Min Act: -0.1700
Data Index: 413716 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.5271. Min Act: -0.1700
Data Index: 6397529 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.4958. Min Act: -0.1700
Data Index: 5736486 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.4958. Min Act: -0.1700
Data Index: 7210819 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.4958. Min Act: -0.1700
Data Index: 6696132 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.4646. Min Act: -0.1700
Data Index: 3290611 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.4646. Min Act: -0.1700
Data Index: 3815796 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9021. Min Range: -6.9021
Max Act: 6.4646. Min Act: -0.1700
Data Index: 4497928 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19