Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4501 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.8908. Min Act: -0.1700
Data Index: 4139058 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.7971. Min Act: -0.1700
Data Index: 6660313 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.6721. Min Act: -0.1700
Data Index: 2359139 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.6408. Min Act: -0.1700
Data Index: 6508685 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.5783. Min Act: -0.1700
Data Index: 1784331 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.5158. Min Act: -0.1700
Data Index: 1038085 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.4533. Min Act: -0.1700
Data Index: 5058187 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.4846. Min Act: -0.1700
Data Index: 3607468 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.4221. Min Act: -0.1700
Data Index: 5352385 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.3908. Min Act: -0.1700
Data Index: 5680647 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.3908. Min Act: -0.1700
Data Index: 3403813 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.3908. Min Act: -0.1700
Data Index: 7316559 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.3283. Min Act: -0.1700
Data Index: 8621427 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.2971. Min Act: -0.1700
Data Index: 3032706 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.2971. Min Act: -0.1700
Data Index: 6600743 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.2971. Min Act: -0.1700
Data Index: 1394039 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.2971. Min Act: -0.1700
Data Index: 134585 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.2658. Min Act: -0.1700
Data Index: 1942162 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.2658. Min Act: -0.1700
Data Index: 5370521 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8908. Min Range: -5.8908
Max Act: 5.2658. Min Act: -0.1700
Data Index: 5908546 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19