Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5326 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.2784. Min Act: -0.1700
Data Index: 8627480 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.2159. Min Act: -0.1700
Data Index: 5112045 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.2159. Min Act: -0.1700
Data Index: 648755 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.2159. Min Act: -0.1700
Data Index: 817750 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.2159. Min Act: -0.1700
Data Index: 52798 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.1534. Min Act: -0.1700
Data Index: 651509 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0909. Min Act: -0.1700
Data Index: 5941062 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0909. Min Act: -0.1700
Data Index: 8076596 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0597. Min Act: -0.1700
Data Index: 7394128 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0909. Min Act: -0.1700
Data Index: 3223674 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 1235118 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 5871434 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 1315670 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 4314693 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2784. Min Range: -5.2784
Max Act: 5.0284. Min Act: -0.1700
Data Index: 4528288 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2784. Min Range: -5.2784
Max Act: 4.9972. Min Act: -0.1700
Data Index: 4412224 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2784. Min Range: -5.2784
Max Act: 4.9972. Min Act: -0.1700
Data Index: 2734083 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2784. Min Range: -5.2784
Max Act: 4.9972. Min Act: -0.1700
Data Index: 4021629 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2784. Min Range: -5.2784
Max Act: 4.9659. Min Act: -0.1700
Data Index: 7910500 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2784. Min Range: -5.2784
Max Act: 4.9659. Min Act: -0.1700
Data Index: 8079294 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19