Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2152 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.6466. Min Act: -0.1700
Data Index: 6156309 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.5015. Min Act: -0.1700
Data Index: 7829790 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4853. Min Act: -0.1700
Data Index: 8363819 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4853. Min Act: -0.1700
Data Index: 4352922 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4529. Min Act: -0.1700
Data Index: 7471249 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4853. Min Act: -0.1700
Data Index: 2760689 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4691. Min Act: -0.1700
Data Index: 7578830 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4529. Min Act: -0.1700
Data Index: 4847205 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4203. Min Act: -0.1700
Data Index: 1341019 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4040. Min Act: -0.1700
Data Index: 5597242 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4040. Min Act: -0.1700
Data Index: 8196640 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.4040. Min Act: -0.1700
Data Index: 2229980 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3877. Min Act: -0.1700
Data Index: 4770632 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3877. Min Act: -0.1700
Data Index: 4975357 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3713. Min Act: -0.1700
Data Index: 2779423 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3713. Min Act: -0.1700
Data Index: 4115514 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3550. Min Act: -0.1700
Data Index: 3398778 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3386. Min Act: -0.1700
Data Index: 7157853 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3386. Min Act: -0.1700
Data Index: 1341020 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6466. Min Range: -2.6466
Max Act: 2.3057. Min Act: -0.1700
Data Index: 4214432 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #19