Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6073 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.8541. Min Act: -0.1700
Data Index: 5718194 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6041. Min Act: -0.1700
Data Index: 1392986 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.4478. Min Act: -0.1700
Data Index: 5536422 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.4478. Min Act: -0.1700
Data Index: 4142733 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.3853. Min Act: -0.1700
Data Index: 7458536 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.3853. Min Act: -0.1700
Data Index: 6025437 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.3540. Min Act: -0.1700
Data Index: 454579 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.3853. Min Act: -0.1700
Data Index: 8673229 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2915. Min Act: -0.1700
Data Index: 1796321 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2915. Min Act: -0.1700
Data Index: 442263 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2915. Min Act: -0.1700
Data Index: 4584099 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2603. Min Act: -0.1700
Data Index: 4266553 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2290. Min Act: -0.1700
Data Index: 4492610 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2290. Min Act: -0.1700
Data Index: 5972557 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2290. Min Act: -0.1700
Data Index: 1131530 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2290. Min Act: -0.1700
Data Index: 1093111 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.2290. Min Act: -0.1700
Data Index: 6171325 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.1978. Min Act: -0.1700
Data Index: 518974 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.1978. Min Act: -0.1700
Data Index: 4142734 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.1978. Min Act: -0.1700
Data Index: 2384335 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19