Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4640 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.5720. Min Act: -0.1700
Data Index: 6478070 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.4157. Min Act: -0.1700
Data Index: 2807866 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.4157. Min Act: -0.1700
Data Index: 6782300 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.3220. Min Act: -0.1700
Data Index: 2932924 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.1970. Min Act: -0.1700
Data Index: 946682 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.2282. Min Act: -0.1700
Data Index: 5360978 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.1970. Min Act: -0.1700
Data Index: 8530140 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.2282. Min Act: -0.1700
Data Index: 8612811 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.1657. Min Act: -0.1700
Data Index: 2196881 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.1345. Min Act: -0.1700
Data Index: 2305135 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.1032. Min Act: -0.1700
Data Index: 1017145 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.1032. Min Act: -0.1700
Data Index: 8269067 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0720. Min Act: -0.1700
Data Index: 520408 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0407. Min Act: -0.1700
Data Index: 8366077 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0720. Min Act: -0.1700
Data Index: 2844906 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0407. Min Act: -0.1700
Data Index: 5313683 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0720. Min Act: -0.1700
Data Index: 8290447 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0407. Min Act: -0.1700
Data Index: 4502816 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0095. Min Act: -0.1700
Data Index: 2938631 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5720. Min Range: -6.5720
Max Act: 6.0407. Min Act: -0.1700
Data Index: 4505666 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19