Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2452 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6860. Min Act: -0.1700
Data Index: 6700544 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6860. Min Act: -0.1700
Data Index: 3781512 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6699. Min Act: -0.1700
Data Index: 4893858 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6539. Min Act: -0.1700
Data Index: 2822294 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6539. Min Act: -0.1700
Data Index: 6461091 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6379. Min Act: -0.1700
Data Index: 5813751 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6379. Min Act: -0.1700
Data Index: 4198086 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6379. Min Act: -0.1700
Data Index: 3996625 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6218. Min Act: -0.1700
Data Index: 1766265 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6218. Min Act: -0.1700
Data Index: 2004689 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6218. Min Act: -0.1700
Data Index: 4832830 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6218. Min Act: -0.1700
Data Index: 4780981 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6218. Min Act: -0.1700
Data Index: 7016685 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6218. Min Act: -0.1700
Data Index: 8737484 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6218. Min Act: -0.1700
Data Index: 4058544 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6057. Min Act: -0.1700
Data Index: 1789373 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6057. Min Act: -0.1700
Data Index: 1931294 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6057. Min Act: -0.1700
Data Index: 763933 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6057. Min Act: -0.1700
Data Index: 2535770 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6860. Min Range: -2.6860
Max Act: 2.6057. Min Act: -0.1700
Data Index: 6301874 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19