Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3192 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5344. Min Range: -8.5344
Max Act: 8.5344. Min Act: -0.1700
Data Index: 8803885 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5344. Min Range: -8.5344
Max Act: 8.4719. Min Act: -0.1700
Data Index: 7836031 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5344. Min Range: -8.5344
Max Act: 8.4094. Min Act: -0.1700
Data Index: 4112148 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5344. Min Range: -8.5344
Max Act: 8.4094. Min Act: -0.1700
Data Index: 542357 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5344. Min Range: -8.5344
Max Act: 8.0031. Min Act: -0.1700
Data Index: 2801320 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5344. Min Range: -8.5344
Max Act: 8.0031. Min Act: -0.1700
Data Index: 1745936 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.9406. Min Act: -0.1700
Data Index: 4418274 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.9094. Min Act: -0.1700
Data Index: 8526922 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.9094. Min Act: -0.1700
Data Index: 7063349 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.8469. Min Act: -0.1700
Data Index: 3900914 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.8469. Min Act: -0.1700
Data Index: 8596374 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.8156. Min Act: -0.1700
Data Index: 8347893 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.8156. Min Act: -0.1700
Data Index: 2878380 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.8156. Min Act: -0.1700
Data Index: 542356 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.6906. Min Act: -0.1700
Data Index: 802771 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.6281. Min Act: -0.1700
Data Index: 5502956 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.5656. Min Act: -0.1700
Data Index: 7244551 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.5656. Min Act: -0.1700
Data Index: 2801319 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.5656. Min Act: -0.1700
Data Index: 8596373 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5344. Min Range: -8.5344
Max Act: 7.5656. Min Act: -0.1700
Data Index: 2893614 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19