Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0036. Min Range: -7.0036
Max Act: 7.0036. Min Act: -0.1700
Data Index: 7734857 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.9411. Min Act: -0.1700
Data Index: 8022745 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.9099. Min Act: -0.1700
Data Index: 4344019 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 8537573 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 2239054 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.7224. Min Act: -0.1700
Data Index: 7982532 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.6911. Min Act: -0.1700
Data Index: 3244505 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.6911. Min Act: -0.1700
Data Index: 5196415 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.6599. Min Act: -0.1700
Data Index: 7959294 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.6599. Min Act: -0.1700
Data Index: 4868038 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.5974. Min Act: -0.1700
Data Index: 2709944 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.5974. Min Act: -0.1700
Data Index: 422490 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.5974. Min Act: -0.1700
Data Index: 2656581 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.5661. Min Act: -0.1700
Data Index: 1122729 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.5349. Min Act: -0.1700
Data Index: 3453591 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.5036. Min Act: -0.1700
Data Index: 7064400 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.4724. Min Act: -0.1700
Data Index: 4634070 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.4724. Min Act: -0.1700
Data Index: 6014744 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.4724. Min Act: -0.1700
Data Index: 4665072 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0036. Min Range: -7.0036
Max Act: 6.4724. Min Act: -0.1700
Data Index: 5267734 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19