Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5646 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.6416. Min Act: -0.1700
Data Index: 1104683 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.5166. Min Act: -0.1700
Data Index: 4843380 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.4854. Min Act: -0.1700
Data Index: 6142657 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.4229. Min Act: -0.1700
Data Index: 3908021 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.4229. Min Act: -0.1700
Data Index: 8265036 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.3916. Min Act: -0.1700
Data Index: 4963678 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.3291. Min Act: -0.1700
Data Index: 4704668 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.3604. Min Act: -0.1700
Data Index: 4060053 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.3291. Min Act: -0.1700
Data Index: 3426471 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.3291. Min Act: -0.1700
Data Index: 8363747 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.2979. Min Act: -0.1700
Data Index: 5657125 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.2979. Min Act: -0.1700
Data Index: 4178979 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.2666. Min Act: -0.1700
Data Index: 1651631 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.2354. Min Act: -0.1700
Data Index: 4910232 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.2354. Min Act: -0.1700
Data Index: 4584794 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.2041. Min Act: -0.1700
Data Index: 5349159 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.1729. Min Act: -0.1700
Data Index: 1314837 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.1729. Min Act: -0.1700
Data Index: 5857446 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.1729. Min Act: -0.1700
Data Index: 2434923 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6416. Min Range: -5.6416
Max Act: 5.1729. Min Act: -0.1700
Data Index: 3563028 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19