Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3689 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.6029. Min Act: -0.1700
Data Index: 744064 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.6029. Min Act: -0.1700
Data Index: 1214140 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.5092. Min Act: -0.1700
Data Index: 5488546 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.5092. Min Act: -0.1700
Data Index: 8788251 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.4779. Min Act: -0.1700
Data Index: 2288708 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.4467. Min Act: -0.1700
Data Index: 6261792 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.4467. Min Act: -0.1700
Data Index: 1814553 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.3842. Min Act: -0.1700
Data Index: 7110699 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.3217. Min Act: -0.1700
Data Index: 4759185 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.3842. Min Act: -0.1700
Data Index: 1777883 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2904. Min Act: -0.1700
Data Index: 3947016 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2904. Min Act: -0.1700
Data Index: 5883798 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2904. Min Act: -0.1700
Data Index: 7971264 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2904. Min Act: -0.1700
Data Index: 5263348 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2592. Min Act: -0.1700
Data Index: 7399510 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2592. Min Act: -0.1700
Data Index: 7798513 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2904. Min Act: -0.1700
Data Index: 2184296 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2279. Min Act: -0.1700
Data Index: 366438 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2279. Min Act: -0.1700
Data Index: 7740163 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6029. Min Range: -5.6029
Max Act: 5.2279. Min Act: -0.1700
Data Index: 4761971 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19