Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1730 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8265. Min Range: -8.8265
Max Act: 8.8265. Min Act: -0.1700
Data Index: 5384358 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8265. Min Range: -8.8265
Max Act: 8.2640. Min Act: -0.1700
Data Index: 4503128 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8265. Min Range: -8.8265
Max Act: 8.2015. Min Act: -0.1700
Data Index: 7420457 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8265. Min Range: -8.8265
Max Act: 8.1390. Min Act: -0.1700
Data Index: 1206345 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.9828. Min Act: -0.1700
Data Index: 4350961 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8265. Min Range: -8.8265
Max Act: 8.0140. Min Act: -0.1700
Data Index: 8268745 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.9515. Min Act: -0.1700
Data Index: 8588125 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.9515. Min Act: -0.1700
Data Index: 5071283 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.9515. Min Act: -0.1700
Data Index: 8428089 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7953. Min Act: -0.1700
Data Index: 3952812 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7953. Min Act: -0.1700
Data Index: 6833665 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7953. Min Act: -0.1700
Data Index: 7263474 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7640. Min Act: -0.1700
Data Index: 2585210 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7328. Min Act: -0.1700
Data Index: 5214236 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7640. Min Act: -0.1700
Data Index: 4820820 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7328. Min Act: -0.1700
Data Index: 921121 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7328. Min Act: -0.1700
Data Index: 3657932 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7015. Min Act: -0.1700
Data Index: 4230414 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7015. Min Act: -0.1700
Data Index: 6428622 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8265. Min Range: -8.8265
Max Act: 7.7015. Min Act: -0.1700
Data Index: 3045374 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19