Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5002 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.2461. Min Act: -0.1700
Data Index: 876512 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.1836. Min Act: -0.1700
Data Index: 8227856 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.1211. Min Act: -0.1700
Data Index: 6203002 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.1211. Min Act: -0.1700
Data Index: 639753 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.1211. Min Act: -0.1700
Data Index: 2124510 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.1211. Min Act: -0.1700
Data Index: 8115870 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.1211. Min Act: -0.1700
Data Index: 6276877 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.1211. Min Act: -0.1700
Data Index: 5986695 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9961. Min Act: -0.1700
Data Index: 7415210 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.0586. Min Act: -0.1700
Data Index: 8512657 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.0586. Min Act: -0.1700
Data Index: 4224242 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2461. Min Range: -7.2461
Max Act: 7.0586. Min Act: -0.1700
Data Index: 5407864 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9961. Min Act: -0.1700
Data Index: 7812374 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9961. Min Act: -0.1700
Data Index: 7462110 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9961. Min Act: -0.1700
Data Index: 4187682 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9961. Min Act: -0.1700
Data Index: 6790383 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9961. Min Act: -0.1700
Data Index: 951105 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9961. Min Act: -0.1700
Data Index: 5436864 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9336. Min Act: -0.1700
Data Index: 4445676 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2461. Min Range: -7.2461
Max Act: 6.9336. Min Act: -0.1700
Data Index: 4445675 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19