Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0150. Min Range: -9.0150
Max Act: 9.0150. Min Act: -0.1700
Data Index: 2336351 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0150. Min Range: -9.0150
Max Act: 8.0775. Min Act: -0.1700
Data Index: 730642 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0150. Min Range: -9.0150
Max Act: 8.0463. Min Act: -0.1700
Data Index: 5000492 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0150. Min Range: -9.0150
Max Act: 8.0150. Min Act: -0.1700
Data Index: 209541 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.9525. Min Act: -0.1700
Data Index: 2675420 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.7963. Min Act: -0.1700
Data Index: 8801887 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.7650. Min Act: -0.1700
Data Index: 3622448 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.7338. Min Act: -0.1700
Data Index: 1329147 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.7025. Min Act: -0.1700
Data Index: 3496085 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.7025. Min Act: -0.1700
Data Index: 2351395 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.6400. Min Act: -0.1700
Data Index: 2781441 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.6088. Min Act: -0.1700
Data Index: 2917197 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.6088. Min Act: -0.1700
Data Index: 2317639 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.5775. Min Act: -0.1700
Data Index: 3528009 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.5775. Min Act: -0.1700
Data Index: 2523178 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.5150. Min Act: -0.1700
Data Index: 6127832 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.5150. Min Act: -0.1700
Data Index: 2917199 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.4838. Min Act: -0.1700
Data Index: 1851458 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.4838. Min Act: -0.1700
Data Index: 7694068 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0150. Min Range: -9.0150
Max Act: 7.4838. Min Act: -0.1700
Data Index: 7915567 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19