Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2586 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2690. Min Range: -7.2690
Max Act: 7.2690. Min Act: -0.1700
Data Index: 249119 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2690. Min Range: -7.2690
Max Act: 7.1753. Min Act: -0.1700
Data Index: 585880 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2690. Min Range: -7.2690
Max Act: 7.1753. Min Act: -0.1700
Data Index: 4833634 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2690. Min Range: -7.2690
Max Act: 7.1128. Min Act: -0.1700
Data Index: 5407710 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2690. Min Range: -7.2690
Max Act: 7.0815. Min Act: -0.1700
Data Index: 3412008 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2690. Min Range: -7.2690
Max Act: 7.0190. Min Act: -0.1700
Data Index: 3756585 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2690. Min Range: -7.2690
Max Act: 7.0190. Min Act: -0.1700
Data Index: 8506464 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.9878. Min Act: -0.1700
Data Index: 4553115 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.9565. Min Act: -0.1700
Data Index: 5960277 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.9565. Min Act: -0.1700
Data Index: 6186845 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.9253. Min Act: -0.1700
Data Index: 5857811 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.9253. Min Act: -0.1700
Data Index: 7978554 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8940. Min Act: -0.1700
Data Index: 8297901 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8628. Min Act: -0.1700
Data Index: 1117642 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8628. Min Act: -0.1700
Data Index: 997704 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8628. Min Act: -0.1700
Data Index: 1277067 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8315. Min Act: -0.1700
Data Index: 3642364 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8940. Min Act: -0.1700
Data Index: 4806290 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8628. Min Act: -0.1700
Data Index: 1374518 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2690. Min Range: -7.2690
Max Act: 6.8315. Min Act: -0.1700
Data Index: 711461 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19