Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 390 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0150. Min Range: -7.0150
Max Act: 7.0150. Min Act: -0.1700
Data Index: 7103924 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.7963. Min Act: -0.1700
Data Index: 7821759 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.7338. Min Act: -0.1700
Data Index: 5540706 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.6713. Min Act: -0.1700
Data Index: 2468884 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.6713. Min Act: -0.1700
Data Index: 1044009 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.5463. Min Act: -0.1700
Data Index: 3829182 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.5463. Min Act: -0.1700
Data Index: 2515908 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.5463. Min Act: -0.1700
Data Index: 5139117 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4838. Min Act: -0.1700
Data Index: 773971 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.5150. Min Act: -0.1700
Data Index: 5598329 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4838. Min Act: -0.1700
Data Index: 1260764 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4838. Min Act: -0.1700
Data Index: 3684204 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4838. Min Act: -0.1700
Data Index: 4388501 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4525. Min Act: -0.1700
Data Index: 5234767 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4213. Min Act: -0.1700
Data Index: 8701726 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4525. Min Act: -0.1700
Data Index: 8035558 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4525. Min Act: -0.1700
Data Index: 7418031 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4213. Min Act: -0.1700
Data Index: 3703475 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.4213. Min Act: -0.1700
Data Index: 350647 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0150. Min Range: -7.0150
Max Act: 6.3900. Min Act: -0.1700
Data Index: 925998 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19