Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.5248. Min Act: -0.1700
Data Index: 1916467 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.3373. Min Act: -0.1700
Data Index: 2569722 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.3061. Min Act: -0.1700
Data Index: 7011075 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.3061. Min Act: -0.1700
Data Index: 6705465 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.2748. Min Act: -0.1700
Data Index: 2392306 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.2748. Min Act: -0.1700
Data Index: 3059939 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.2123. Min Act: -0.1700
Data Index: 203547 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.2123. Min Act: -0.1700
Data Index: 1383847 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.1811. Min Act: -0.1700
Data Index: 5410869 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.1498. Min Act: -0.1700
Data Index: 5326195 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.1498. Min Act: -0.1700
Data Index: 4509128 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.0873. Min Act: -0.1700
Data Index: 460999 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.0561. Min Act: -0.1700
Data Index: 8350838 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.0561. Min Act: -0.1700
Data Index: 1813950 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.0561. Min Act: -0.1700
Data Index: 1606 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5248. Min Range: -5.5248
Max Act: 5.0873. Min Act: -0.1700
Data Index: 3499784 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5248. Min Range: -5.5248
Max Act: 4.9936. Min Act: -0.1700
Data Index: 5797770 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5248. Min Range: -5.5248
Max Act: 4.9936. Min Act: -0.1700
Data Index: 3205844 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5248. Min Range: -5.5248
Max Act: 4.9623. Min Act: -0.1700
Data Index: 6167593 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5248. Min Range: -5.5248
Max Act: 4.9623. Min Act: -0.1700
Data Index: 988988 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19