Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2074 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.3581. Min Act: -0.1700
Data Index: 5574908 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.3581. Min Act: -0.1700
Data Index: 583144 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.3269. Min Act: -0.1700
Data Index: 4042410 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.2956. Min Act: -0.1700
Data Index: 6932628 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.2956. Min Act: -0.1700
Data Index: 6254390 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.2019. Min Act: -0.1700
Data Index: 5406384 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.1706. Min Act: -0.1700
Data Index: 7068490 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.1394. Min Act: -0.1700
Data Index: 6803441 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.1394. Min Act: -0.1700
Data Index: 1305149 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.1394. Min Act: -0.1700
Data Index: 7741400 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.1081. Min Act: -0.1700
Data Index: 3788265 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0769. Min Act: -0.1700
Data Index: 2482264 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0456. Min Act: -0.1700
Data Index: 634211 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0456. Min Act: -0.1700
Data Index: 7648306 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0456. Min Act: -0.1700
Data Index: 2259955 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0456. Min Act: -0.1700
Data Index: 6635085 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0456. Min Act: -0.1700
Data Index: 8739429 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0144. Min Act: -0.1700
Data Index: 6076942 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0456. Min Act: -0.1700
Data Index: 1031288 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3581. Min Range: -5.3581
Max Act: 5.0144. Min Act: -0.1700
Data Index: 3669490 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19