Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 506 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5536. Min Range: -11.5536
Max Act: 11.5536. Min Act: -0.1700
Data Index: 6305225 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5536. Min Range: -11.5536
Max Act: 11.3661. Min Act: -0.1700
Data Index: 5276264 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5536. Min Range: -11.5536
Max Act: 11.3661. Min Act: -0.1700
Data Index: 2473601 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5536. Min Range: -11.5536
Max Act: 11.1161. Min Act: -0.1700
Data Index: 2647494 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.9911. Min Act: -0.1700
Data Index: 7241357 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.9911. Min Act: -0.1700
Data Index: 673617 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.9286. Min Act: -0.1700
Data Index: 6140906 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.9286. Min Act: -0.1700
Data Index: 1248920 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.8661. Min Act: -0.1700
Data Index: 7217672 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.7411. Min Act: -0.1700
Data Index: 4689598 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.7411. Min Act: -0.1700
Data Index: 1718965 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.7411. Min Act: -0.1700
Data Index: 6377239 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.6786. Min Act: -0.1700
Data Index: 2511176 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.6786. Min Act: -0.1700
Data Index: 4598910 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.6786. Min Act: -0.1700
Data Index: 2845248 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.6161. Min Act: -0.1700
Data Index: 8002370 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.5536. Min Act: -0.1700
Data Index: 5783099 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.4911. Min Act: -0.1700
Data Index: 5257077 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.4286. Min Act: -0.1700
Data Index: 554011 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5536. Min Range: -11.5536
Max Act: 10.4911. Min Act: -0.1700
Data Index: 5770478 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19