Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4435 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0565. Min Range: -11.0565
Max Act: 11.0565. Min Act: -0.1700
Data Index: 6452914 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.9940. Min Act: -0.1700
Data Index: 7551977 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.6190. Min Act: -0.1700
Data Index: 819768 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.4940. Min Act: -0.1700
Data Index: 958780 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.3690. Min Act: -0.1700
Data Index: 6394105 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.3065. Min Act: -0.1700
Data Index: 3717377 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.2440. Min Act: -0.1699
Data Index: 1354522 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.2440. Min Act: -0.1700
Data Index: 415422 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.1815. Min Act: -0.1700
Data Index: 674811 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.2440. Min Act: -0.1700
Data Index: 5305129 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.1190. Min Act: -0.1700
Data Index: 5444798 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.1815. Min Act: -0.1700
Data Index: 4670818 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.1815. Min Act: -0.1700
Data Index: 6026772 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.1190. Min Act: -0.1700
Data Index: 7987540 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.1190. Min Act: -0.1700
Data Index: 4261011 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.0565. Min Act: -0.1700
Data Index: 6049475 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.0565. Min Act: -0.1700
Data Index: 5254458 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.0565. Min Act: -0.1700
Data Index: 4541414 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0565. Min Range: -11.0565
Max Act: 10.0565. Min Act: -0.1700
Data Index: 7291850 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0565. Min Range: -11.0565
Max Act: 9.9940. Min Act: -0.1700
Data Index: 3221931 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19