Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2020 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.7234. Min Act: -0.1700
Data Index: 901740 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.6609. Min Act: -0.1700
Data Index: 7387613 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.6296. Min Act: -0.1700
Data Index: 5219300 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.6296. Min Act: -0.1700
Data Index: 8787130 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5671. Min Act: -0.1700
Data Index: 2473175 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5359. Min Act: -0.1700
Data Index: 5816294 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5671. Min Act: -0.1700
Data Index: 4236807 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5671. Min Act: -0.1700
Data Index: 871488 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5671. Min Act: -0.1700
Data Index: 6084270 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5359. Min Act: -0.1700
Data Index: 7295555 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6339799 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5359. Min Act: -0.1700
Data Index: 2155437 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5359. Min Act: -0.1700
Data Index: 6440331 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5046. Min Act: -0.1700
Data Index: 1535316 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.4734. Min Act: -0.1700
Data Index: 7799799 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5046. Min Act: -0.1700
Data Index: 1489149 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5046. Min Act: -0.1700
Data Index: 4224612 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.5046. Min Act: -0.1700
Data Index: 6024482 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.4734. Min Act: -0.1700
Data Index: 4049622 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7234. Min Range: -5.7234
Max Act: 5.4734. Min Act: -0.1700
Data Index: 6449741 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19