Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4804 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.3541. Min Act: -0.1700
Data Index: 5347053 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.3228. Min Act: -0.1700
Data Index: 1349367 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.2603. Min Act: -0.1700
Data Index: 2326494 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.2603. Min Act: -0.1700
Data Index: 7753439 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.2291. Min Act: -0.1700
Data Index: 1000626 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.1666. Min Act: -0.1700
Data Index: 5562788 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.0416. Min Act: -0.1700
Data Index: 7999820 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.0103. Min Act: -0.1700
Data Index: 349998 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3541. Min Range: -6.3541
Max Act: 6.0103. Min Act: -0.1700
Data Index: 5044842 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.9791. Min Act: -0.1700
Data Index: 8541466 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.9791. Min Act: -0.1700
Data Index: 5949325 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.9166. Min Act: -0.1700
Data Index: 4798335 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8853. Min Act: -0.1700
Data Index: 4987501 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8853. Min Act: -0.1700
Data Index: 8654356 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8228. Min Act: -0.1700
Data Index: 2175123 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8541. Min Act: -0.1700
Data Index: 989534 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8541. Min Act: -0.1700
Data Index: 6606906 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8228. Min Act: -0.1700
Data Index: 7701163 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8228. Min Act: -0.1700
Data Index: 6069211 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3541. Min Range: -6.3541
Max Act: 5.8228. Min Act: -0.1700
Data Index: 2523001 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19