Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1827 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.1155. Min Range: -9.1155
Max Act: 9.1155. Min Act: -0.1700
Data Index: 516427 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.9905. Min Act: -0.1700
Data Index: 6479115 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.9280. Min Act: -0.1700
Data Index: 6223816 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.7405. Min Act: -0.1700
Data Index: 4756144 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.8030. Min Act: -0.1700
Data Index: 5727049 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.8030. Min Act: -0.1700
Data Index: 7814232 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6780. Min Act: -0.1700
Data Index: 3626218 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6780. Min Act: -0.1700
Data Index: 3867092 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.7405. Min Act: -0.1700
Data Index: 7624193 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6780. Min Act: -0.1700
Data Index: 5100988 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.7405. Min Act: -0.1700
Data Index: 6253248 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.7405. Min Act: -0.1700
Data Index: 7588362 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6780. Min Act: -0.1700
Data Index: 7302392 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6780. Min Act: -0.1700
Data Index: 5995055 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6780. Min Act: -0.1700
Data Index: 1154000 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6155. Min Act: -0.1699
Data Index: 4517132 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6155. Min Act: -0.1700
Data Index: 5209184 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.5530. Min Act: -0.1700
Data Index: 4177486 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6155. Min Act: -0.1700
Data Index: 5212153 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1155. Min Range: -9.1155
Max Act: 8.6155. Min Act: -0.1700
Data Index: 6389211 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19