Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.5070. Min Act: -0.1700
Data Index: 3422961 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.4757. Min Act: -0.1700
Data Index: 8532068 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.4287. Min Act: -0.1700
Data Index: 4881745 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.3189. Min Act: -0.1700
Data Index: 8060322 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.3189. Min Act: -0.1700
Data Index: 5983394 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.3032. Min Act: -0.1700
Data Index: 5283650 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.2875. Min Act: -0.1700
Data Index: 6008092 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.2561. Min Act: -0.1700
Data Index: 694483 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.2561. Min Act: -0.1700
Data Index: 6428688 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.2404. Min Act: -0.1700
Data Index: 8177373 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.2246. Min Act: -0.1700
Data Index: 7196492 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.1775. Min Act: -0.1700
Data Index: 5967626 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.2089. Min Act: -0.1700
Data Index: 5719195 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.2089. Min Act: -0.1700
Data Index: 6910254 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.1775. Min Act: -0.1700
Data Index: 5970153 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.1775. Min Act: -0.1700
Data Index: 4963400 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.1617. Min Act: -0.1700
Data Index: 1677372 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.1460. Min Act: -0.1700
Data Index: 8392998 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.1617. Min Act: -0.1700
Data Index: 633812 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5070. Min Range: -3.5070
Max Act: 3.1302. Min Act: -0.1700
Data Index: 3154732 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19