Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4590 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.8585. Min Act: -0.1700
Data Index: 5669498 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.7960. Min Act: -0.1700
Data Index: 8783933 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.7647. Min Act: -0.1700
Data Index: 3054460 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.7647. Min Act: -0.1700
Data Index: 5219825 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.7335. Min Act: -0.1700
Data Index: 4043975 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.7022. Min Act: -0.1700
Data Index: 4369112 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.6710. Min Act: -0.1700
Data Index: 7355440 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.6710. Min Act: -0.1700
Data Index: 4832503 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.6397. Min Act: -0.1700
Data Index: 5752491 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.6085. Min Act: -0.1700
Data Index: 8292058 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.6085. Min Act: -0.1700
Data Index: 46957 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.5772. Min Act: -0.1700
Data Index: 5894281 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.5772. Min Act: -0.1700
Data Index: 948922 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.5772. Min Act: -0.1700
Data Index: 2076961 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.5147. Min Act: -0.1700
Data Index: 3771814 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.5147. Min Act: -0.1700
Data Index: 1532840 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.5460. Min Act: -0.1700
Data Index: 708418 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.5147. Min Act: -0.1700
Data Index: 3282130 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.4835. Min Act: -0.1700
Data Index: 7147133 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8585. Min Range: -5.8585
Max Act: 5.4835. Min Act: -0.1700
Data Index: 5076568 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19