Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.4202. Min Act: -0.1700
Data Index: 3848252 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.4202. Min Act: -0.1700
Data Index: 1112482 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.3890. Min Act: -0.1700
Data Index: 3361699 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.3890. Min Act: -0.1700
Data Index: 8759070 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.3890. Min Act: -0.1700
Data Index: 7471243 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.3265. Min Act: -0.1700
Data Index: 5064451 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2952. Min Act: -0.1700
Data Index: 3713044 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2640. Min Act: -0.1700
Data Index: 5038194 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2640. Min Act: -0.1700
Data Index: 3713046 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2640. Min Act: -0.1700
Data Index: 6678810 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2327. Min Act: -0.1700
Data Index: 366227 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2327. Min Act: -0.1700
Data Index: 2320592 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2327. Min Act: -0.1700
Data Index: 8030540 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2327. Min Act: -0.1700
Data Index: 8757752 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2327. Min Act: -0.1700
Data Index: 628577 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2015. Min Act: -0.1700
Data Index: 7029241 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2327. Min Act: -0.1700
Data Index: 4197461 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2015. Min Act: -0.1700
Data Index: 6768848 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.1702. Min Act: -0.1700
Data Index: 5420016 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4202. Min Range: -6.4202
Max Act: 6.2015. Min Act: -0.1700
Data Index: 8239465 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19