Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1472 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.6951. Min Act: -0.1700
Data Index: 2420621 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.5701. Min Act: -0.1700
Data Index: 3666844 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.5701. Min Act: -0.1700
Data Index: 4188494 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.5076. Min Act: -0.1700
Data Index: 4945585 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.4451. Min Act: -0.1700
Data Index: 278241 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 1997944 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.3826. Min Act: -0.1700
Data Index: 6083130 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.2576. Min Act: -0.1700
Data Index: 6907316 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.2576. Min Act: -0.1700
Data Index: 6248240 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.2576. Min Act: -0.1700
Data Index: 6063114 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.1951. Min Act: -0.1700
Data Index: 488949 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.1951. Min Act: -0.1700
Data Index: 5339739 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.1326. Min Act: -0.1700
Data Index: 3441433 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.0701. Min Act: -0.1700
Data Index: 3277383 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.0701. Min Act: -0.1700
Data Index: 676266 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.1326. Min Act: -0.1700
Data Index: 6017421 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.1326. Min Act: -0.1700
Data Index: 288522 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.1326. Min Act: -0.1700
Data Index: 6560765 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.0701. Min Act: -0.1700
Data Index: 8603022 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6951. Min Range: -8.6951
Max Act: 8.0701. Min Act: -0.1700
Data Index: 2264160 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19