Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 5610746 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6833. Min Act: -0.1700
Data Index: 946762 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6521. Min Act: -0.1700
Data Index: 41837 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6208. Min Act: -0.1700
Data Index: 8243881 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5896. Min Act: -0.1700
Data Index: 1851129 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.6208. Min Act: -0.1700
Data Index: 7901692 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5896. Min Act: -0.1700
Data Index: 2099574 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5583. Min Act: -0.1700
Data Index: 7207281 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4958. Min Act: -0.1700
Data Index: 1003264 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.5271. Min Act: -0.1700
Data Index: 4464664 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4646. Min Act: -0.1700
Data Index: 6131826 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 3643720 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 7129986 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 2688761 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4333. Min Act: -0.1700
Data Index: 1821211 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.4021. Min Act: -0.1700
Data Index: 42334 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3708. Min Act: -0.1700
Data Index: 2251483 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3708. Min Act: -0.1700
Data Index: 6942726 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3708. Min Act: -0.1700
Data Index: 5467035 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6833. Min Range: -5.6833
Max Act: 5.3396. Min Act: -0.1700
Data Index: 1510079 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19