Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3025 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.8267. Min Act: -0.1700
Data Index: 4717838 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.7955. Min Act: -0.1700
Data Index: 6061299 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.7955. Min Act: -0.1700
Data Index: 7490508 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.7330. Min Act: -0.1700
Data Index: 2539920 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.6392. Min Act: -0.1700
Data Index: 5811323 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.4205. Min Act: -0.1700
Data Index: 6960797 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.3267. Min Act: -0.1700
Data Index: 375987 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.2955. Min Act: -0.1700
Data Index: 4994839 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.2330. Min Act: -0.1700
Data Index: 6545681 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.2017. Min Act: -0.1700
Data Index: 2502212 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1705. Min Act: -0.1700
Data Index: 3491194 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 4898492 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 5610017 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 1870423 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 6166000 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1392. Min Act: -0.1700
Data Index: 5067005 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1080. Min Act: -0.1700
Data Index: 2617010 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1080. Min Act: -0.1700
Data Index: 4735204 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.1080. Min Act: -0.1700
Data Index: 5183092 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8267. Min Range: -5.8267
Max Act: 5.0767. Min Act: -0.1700
Data Index: 3136423 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19