Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.4300. Min Act: -0.1700
Data Index: 323966 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.3987. Min Act: -0.1700
Data Index: 2958624 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.3362. Min Act: -0.1700
Data Index: 383234 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.3362. Min Act: -0.1700
Data Index: 323965 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.3050. Min Act: -0.1700
Data Index: 6497450 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.3050. Min Act: -0.1700
Data Index: 870501 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.2737. Min Act: -0.1700
Data Index: 8349229 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.2737. Min Act: -0.1700
Data Index: 4147079 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.2737. Min Act: -0.1700
Data Index: 5255791 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1800. Min Act: -0.1700
Data Index: 8051132 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1800. Min Act: -0.1700
Data Index: 7544102 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1800. Min Act: -0.1700
Data Index: 609915 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1487. Min Act: -0.1700
Data Index: 1604275 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1487. Min Act: -0.1700
Data Index: 4676498 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1487. Min Act: -0.1700
Data Index: 8141777 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1487. Min Act: -0.1700
Data Index: 819537 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1487. Min Act: -0.1700
Data Index: 4063236 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.1175. Min Act: -0.1700
Data Index: 2978731 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.0862. Min Act: -0.1700
Data Index: 7518922 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4300. Min Range: -7.4300
Max Act: 7.0862. Min Act: -0.1700
Data Index: 5961770 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19