Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1986 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.9578. Min Act: -0.1700
Data Index: 6532505 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.9265. Min Act: -0.1700
Data Index: 4165076 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.8953. Min Act: -0.1700
Data Index: 7048100 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.7703. Min Act: -0.1700
Data Index: 8038132 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.7078. Min Act: -0.1700
Data Index: 222616 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.6765. Min Act: -0.1700
Data Index: 7720394 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.6140. Min Act: -0.1700
Data Index: 2032270 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.4890. Min Act: -0.1700
Data Index: 672132 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.4265. Min Act: -0.1700
Data Index: 7534268 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.3953. Min Act: -0.1700
Data Index: 5705307 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.3953. Min Act: -0.1700
Data Index: 1368450 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.3640. Min Act: -0.1700
Data Index: 3981115 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.3328. Min Act: -0.1700
Data Index: 7196205 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.3640. Min Act: -0.1700
Data Index: 7729148 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.3328. Min Act: -0.1700
Data Index: 7427649 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.2703. Min Act: -0.1700
Data Index: 6781385 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.2703. Min Act: -0.1700
Data Index: 5275234 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.2703. Min Act: -0.1700
Data Index: 247789 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.2390. Min Act: -0.1700
Data Index: 5563889 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9578. Min Range: -6.9578
Max Act: 6.2078. Min Act: -0.1700
Data Index: 7660889 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19