Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.4343. Min Act: -0.1700
Data Index: 7969956 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.3718. Min Act: -0.1700
Data Index: 5933437 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.3405. Min Act: -0.1700
Data Index: 7877458 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.3405. Min Act: -0.1700
Data Index: 7212151 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.3718. Min Act: -0.1700
Data Index: 5217749 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.3093. Min Act: -0.1700
Data Index: 3615734 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.3093. Min Act: -0.1700
Data Index: 2842739 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2155. Min Act: -0.1700
Data Index: 4213660 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2467. Min Act: -0.1700
Data Index: 282088 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2467. Min Act: -0.1700
Data Index: 2152026 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2467. Min Act: -0.1700
Data Index: 6719138 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2780. Min Act: -0.1700
Data Index: 1345178 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2467. Min Act: -0.1700
Data Index: 992454 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2467. Min Act: -0.1700
Data Index: 6540992 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2155. Min Act: -0.1700
Data Index: 4008377 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.1842. Min Act: -0.1700
Data Index: 6533772 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2155. Min Act: -0.1700
Data Index: 7568098 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2155. Min Act: -0.1700
Data Index: 6147698 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.1842. Min Act: -0.1700
Data Index: 3768088 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4343. Min Range: -4.4343
Max Act: 4.2155. Min Act: -0.1700
Data Index: 7667998 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19