Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5981 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.8670. Min Act: -0.1700
Data Index: 413147 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.5858. Min Act: -0.1700
Data Index: 4085995 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.5858. Min Act: -0.1700
Data Index: 1137897 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.5858. Min Act: -0.1700
Data Index: 3183525 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.4920. Min Act: -0.1700
Data Index: 5299363 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.4608. Min Act: -0.1700
Data Index: 3559843 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.4295. Min Act: -0.1700
Data Index: 5899516 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.3983. Min Act: -0.1700
Data Index: 6643584 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.3358. Min Act: -0.1700
Data Index: 4385493 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.3670. Min Act: -0.1700
Data Index: 7333396 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.3045. Min Act: -0.1700
Data Index: 6534989 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.2733. Min Act: -0.1700
Data Index: 1188412 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.2733. Min Act: -0.1700
Data Index: 1151065 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.2420. Min Act: -0.1700
Data Index: 4890622 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.2108. Min Act: -0.1700
Data Index: 1512997 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.2108. Min Act: -0.1700
Data Index: 1207060 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.2108. Min Act: -0.1700
Data Index: 4427819 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.2108. Min Act: -0.1700
Data Index: 5699453 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.1795. Min Act: -0.1700
Data Index: 6527167 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8670. Min Range: -5.8670
Max Act: 5.1795. Min Act: -0.1700
Data Index: 5822033 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19