Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 390 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0697. Min Range: -9.0697
Max Act: 9.0697. Min Act: -0.1691
Data Index: 8546416 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.8197. Min Act: -0.1695
Data Index: 7814328 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.6010. Min Act: -0.1700
Data Index: 7051308 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.5385. Min Act: -0.1700
Data Index: 1040543 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.5385. Min Act: -0.1700
Data Index: 1318388 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.5072. Min Act: -0.1700
Data Index: 4600642 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.5385. Min Act: -0.1693
Data Index: 8449840 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.4135. Min Act: -0.1700
Data Index: 5508043 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.4135. Min Act: -0.1700
Data Index: 3577042 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.4135. Min Act: -0.1700
Data Index: 6313501 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.3822. Min Act: -0.1700
Data Index: 5762452 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.3510. Min Act: -0.1700
Data Index: 4936995 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.3197. Min Act: -0.1700
Data Index: 4387312 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.3510. Min Act: -0.1700
Data Index: 3295746 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.3197. Min Act: -0.1696
Data Index: 7733427 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.3197. Min Act: -0.1700
Data Index: 5481897 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.2885. Min Act: -0.1700
Data Index: 6228661 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.2885. Min Act: -0.1680
Data Index: 190406 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.2885. Min Act: -0.1700
Data Index: 3608162 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0697. Min Range: -9.0697
Max Act: 8.2885. Min Act: -0.1700
Data Index: 7312280 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19