Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2540 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.3790. Min Act: -0.1700
Data Index: 5999602 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.3165. Min Act: -0.1700
Data Index: 6885010 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2852. Min Act: -0.1700
Data Index: 5324698 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2852. Min Act: -0.1700
Data Index: 6673304 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2540. Min Act: -0.1700
Data Index: 7931009 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2852. Min Act: -0.1700
Data Index: 8602607 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2540. Min Act: -0.1700
Data Index: 6965693 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2540. Min Act: -0.1700
Data Index: 873620 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2227. Min Act: -0.1700
Data Index: 3236488 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2227. Min Act: -0.1700
Data Index: 900638 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.2227. Min Act: -0.1700
Data Index: 4540092 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1915. Min Act: -0.1700
Data Index: 5644004 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1915. Min Act: -0.1700
Data Index: 5558524 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1602. Min Act: -0.1700
Data Index: 4253791 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1602. Min Act: -0.1700
Data Index: 4603148 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1602. Min Act: -0.1700
Data Index: 8180059 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1290. Min Act: -0.1700
Data Index: 6996978 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1290. Min Act: -0.1700
Data Index: 1324236 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.1290. Min Act: -0.1700
Data Index: 8504681 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3790. Min Range: -7.3790
Max Act: 7.0977. Min Act: -0.1700
Data Index: 4932331 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19