Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 785 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.9888. Min Act: -0.1700
Data Index: 2084015 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.9576. Min Act: -0.1700
Data Index: 2360959 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.8326. Min Act: -0.1700
Data Index: 1227216 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.7701. Min Act: -0.1700
Data Index: 6687808 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.7388. Min Act: -0.1700
Data Index: 1219924 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.7388. Min Act: -0.1700
Data Index: 62670 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6451. Min Act: -0.1700
Data Index: 3911024 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6763. Min Act: -0.1700
Data Index: 170559 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6763. Min Act: -0.1700
Data Index: 2158776 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6451. Min Act: -0.1700
Data Index: 4971078 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6451. Min Act: -0.1700
Data Index: 2607588 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6451. Min Act: -0.1700
Data Index: 8505711 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6138. Min Act: -0.1700
Data Index: 8247126 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6138. Min Act: -0.1700
Data Index: 1720312 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.6138. Min Act: -0.1700
Data Index: 5641874 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.5826. Min Act: -0.1700
Data Index: 6775657 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.5826. Min Act: -0.1700
Data Index: 7076633 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.5201. Min Act: -0.1700
Data Index: 3280105 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.4576. Min Act: -0.1700
Data Index: 7230061 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9888. Min Range: -6.9888
Max Act: 6.4576. Min Act: -0.1700
Data Index: 2253343 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19