Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 188 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1297. Min Range: -9.1297
Max Act: 9.1297. Min Act: -0.1700
Data Index: 8463989 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1297. Min Range: -9.1297
Max Act: 9.0672. Min Act: -0.1700
Data Index: 4442046 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1297. Min Range: -9.1297
Max Act: 9.0047. Min Act: -0.1700
Data Index: 4433017 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1297. Min Range: -9.1297
Max Act: 9.0047. Min Act: -0.1700
Data Index: 5830502 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.8797. Min Act: -0.1700
Data Index: 5023176 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.8797. Min Act: -0.1700
Data Index: 919051 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.8797. Min Act: -0.1700
Data Index: 698963 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.8797. Min Act: -0.1700
Data Index: 8363152 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.8172. Min Act: -0.1700
Data Index: 2762967 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.8172. Min Act: -0.1700
Data Index: 488150 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.7547. Min Act: -0.1700
Data Index: 5360546 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.7547. Min Act: -0.1700
Data Index: 50866 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.6922. Min Act: -0.1700
Data Index: 4406387 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.6922. Min Act: -0.1700
Data Index: 6267219 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.6297. Min Act: -0.1700
Data Index: 5436611 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.6297. Min Act: -0.1700
Data Index: 8299362 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.5672. Min Act: -0.1700
Data Index: 2136248 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.6297. Min Act: -0.1700
Data Index: 4364168 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.6297. Min Act: -0.1700
Data Index: 7523153 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1297. Min Range: -9.1297
Max Act: 8.5672. Min Act: -0.1700
Data Index: 1332891 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19