Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0754. Min Range: -7.0754
Max Act: 7.0754. Min Act: -0.1700
Data Index: 992471 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.9504. Min Act: -0.1700
Data Index: 3030358 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.9192. Min Act: -0.1700
Data Index: 3515065 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.9192. Min Act: -0.1700
Data Index: 6631595 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.9504. Min Act: -0.1700
Data Index: 7968883 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.9192. Min Act: -0.1700
Data Index: 2077737 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8879. Min Act: -0.1700
Data Index: 2381845 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8879. Min Act: -0.1700
Data Index: 1481551 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8879. Min Act: -0.1700
Data Index: 5974788 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8879. Min Act: -0.1700
Data Index: 3811100 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8567. Min Act: -0.1700
Data Index: 7328439 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8567. Min Act: -0.1700
Data Index: 4968979 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8879. Min Act: -0.1700
Data Index: 7021686 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8567. Min Act: -0.1700
Data Index: 6873110 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8567. Min Act: -0.1700
Data Index: 6079132 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8567. Min Act: -0.1700
Data Index: 8642435 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8254. Min Act: -0.1700
Data Index: 2700229 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8254. Min Act: -0.1700
Data Index: 2132317 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.8254. Min Act: -0.1700
Data Index: 6665885 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0754. Min Range: -7.0754
Max Act: 6.7942. Min Act: -0.1700
Data Index: 5389166 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19