Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2874 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.9033. Min Act: -0.1700
Data Index: 8480684 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.9658. Min Act: -0.1700
Data Index: 4210755 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.8096. Min Act: -0.1700
Data Index: 8324178 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.7158. Min Act: -0.1700
Data Index: 1788034 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6533. Min Act: -0.1700
Data Index: 7587340 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6221. Min Act: -0.1700
Data Index: 2545536 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6533. Min Act: -0.1700
Data Index: 2318087 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6221. Min Act: -0.1700
Data Index: 3391791 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6221. Min Act: -0.1700
Data Index: 4885264 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6221. Min Act: -0.1700
Data Index: 2492118 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6221. Min Act: -0.1700
Data Index: 1824425 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.6221. Min Act: -0.1700
Data Index: 1304076 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.5908. Min Act: -0.1700
Data Index: 1852552 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.5596. Min Act: -0.1700
Data Index: 1290507 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.5596. Min Act: -0.1700
Data Index: 7311538 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.5596. Min Act: -0.1700
Data Index: 2314175 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.5596. Min Act: -0.1700
Data Index: 3332281 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.5596. Min Act: -0.1700
Data Index: 971401 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.4971. Min Act: -0.1700
Data Index: 1551306 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9658. Min Range: -6.9658
Max Act: 6.5283. Min Act: -0.1700
Data Index: 7859455 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19