Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4304. Min Range: -8.4304
Max Act: 8.4304. Min Act: -0.1700
Data Index: 6026797 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.8992. Min Act: -0.1700
Data Index: 6666758 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.6179. Min Act: -0.1700
Data Index: 8693125 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.4617. Min Act: -0.1700
Data Index: 2870758 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.3992. Min Act: -0.1700
Data Index: 8323964 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.3054. Min Act: -0.1700
Data Index: 3083380 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.2429. Min Act: -0.1700
Data Index: 7474741 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.2117. Min Act: -0.1700
Data Index: 2949151 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.1804. Min Act: -0.1700
Data Index: 882737 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.1804. Min Act: -0.1700
Data Index: 6152863 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.1179. Min Act: -0.1700
Data Index: 6006006 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.1179. Min Act: -0.1700
Data Index: 4657136 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4304. Min Range: -8.4304
Max Act: 7.0554. Min Act: -0.1700
Data Index: 8329259 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4304. Min Range: -8.4304
Max Act: 6.9929. Min Act: -0.1700
Data Index: 7158616 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4304. Min Range: -8.4304
Max Act: 6.9929. Min Act: -0.1700
Data Index: 8026327 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4304. Min Range: -8.4304
Max Act: 6.9304. Min Act: -0.1700
Data Index: 3884732 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4304. Min Range: -8.4304
Max Act: 6.8992. Min Act: -0.1700
Data Index: 7611894 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4304. Min Range: -8.4304
Max Act: 6.8992. Min Act: -0.1700
Data Index: 8308781 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4304. Min Range: -8.4304
Max Act: 6.8679. Min Act: -0.1700
Data Index: 6157253 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4304. Min Range: -8.4304
Max Act: 6.8679. Min Act: -0.1700
Data Index: 6768096 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19