Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4783 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6472688 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.6596. Min Act: -0.1700
Data Index: 8417318 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3094988 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3128089 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4721. Min Act: -0.1700
Data Index: 5334087 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4721. Min Act: -0.1700
Data Index: 4995463 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4408. Min Act: -0.1700
Data Index: 2381592 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4096. Min Act: -0.1700
Data Index: 1627160 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4096. Min Act: -0.1700
Data Index: 7121318 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4096. Min Act: -0.1700
Data Index: 2603637 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4096. Min Act: -0.1700
Data Index: 6701866 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4096. Min Act: -0.1700
Data Index: 4995462 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.4096. Min Act: -0.1700
Data Index: 8156131 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.3783. Min Act: -0.1700
Data Index: 4332129 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.3783. Min Act: -0.1700
Data Index: 1277509 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.3471. Min Act: -0.1700
Data Index: 3185033 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.3471. Min Act: -0.1700
Data Index: 166607 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.3471. Min Act: -0.1700
Data Index: 4770978 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.3471. Min Act: -0.1700
Data Index: 4222104 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6596. Min Range: -5.6596
Max Act: 5.3471. Min Act: -0.1700
Data Index: 5478507 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19