Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.4150. Min Act: -0.1700
Data Index: 4472973 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.4150. Min Act: -0.1700
Data Index: 945142 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.4150. Min Act: -0.1700
Data Index: 2344354 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.3212. Min Act: -0.1700
Data Index: 1839497 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.3212. Min Act: -0.1700
Data Index: 3947088 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.2900. Min Act: -0.1700
Data Index: 4223695 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.2900. Min Act: -0.1700
Data Index: 6754622 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.2587. Min Act: -0.1700
Data Index: 889288 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.2275. Min Act: -0.1700
Data Index: 3818580 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.2275. Min Act: -0.1700
Data Index: 4324943 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0712. Min Act: -0.1700
Data Index: 1195197 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0712. Min Act: -0.1700
Data Index: 5575955 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0712. Min Act: -0.1700
Data Index: 8372499 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0712. Min Act: -0.1700
Data Index: 6668926 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0712. Min Act: -0.1700
Data Index: 4113062 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0400. Min Act: -0.1700
Data Index: 6766440 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0400. Min Act: -0.1700
Data Index: 2284093 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4150. Min Range: -5.4150
Max Act: 5.0087. Min Act: -0.1700
Data Index: 8825054 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4150. Min Range: -5.4150
Max Act: 4.9775. Min Act: -0.1700
Data Index: 4886412 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4150. Min Range: -5.4150
Max Act: 4.9775. Min Act: -0.1700
Data Index: 4974026 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19