Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.5092. Min Act: -0.1700
Data Index: 2708803 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.4779. Min Act: -0.1700
Data Index: 5643789 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.4779. Min Act: -0.1700
Data Index: 5278162 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.4467. Min Act: -0.1700
Data Index: 6801606 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.2592. Min Act: -0.1700
Data Index: 1934063 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.2279. Min Act: -0.1700
Data Index: 5278159 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.2279. Min Act: -0.1700
Data Index: 3783631 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.2279. Min Act: -0.1700
Data Index: 5278158 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.1967. Min Act: -0.1700
Data Index: 5484680 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.1654. Min Act: -0.1700
Data Index: 3643275 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.1342. Min Act: -0.1700
Data Index: 2601861 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.1029. Min Act: -0.1700
Data Index: 5011936 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.1029. Min Act: -0.1700
Data Index: 5500192 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.0717. Min Act: -0.1700
Data Index: 7100291 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.0717. Min Act: -0.1700
Data Index: 5130552 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.0717. Min Act: -0.1700
Data Index: 1457613 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.0404. Min Act: -0.1700
Data Index: 5278160 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5092. Min Range: -7.5092
Max Act: 7.0092. Min Act: -0.1700
Data Index: 16778 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5092. Min Range: -7.5092
Max Act: 6.9779. Min Act: -0.1700
Data Index: 8425526 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5092. Min Range: -7.5092
Max Act: 6.9779. Min Act: -0.1700
Data Index: 2408955 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19