Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.9935. Min Act: -0.1700
Data Index: 7679379 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.9623. Min Act: -0.1700
Data Index: 1142227 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.9623. Min Act: -0.1700
Data Index: 5773512 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.9623. Min Act: -0.1700
Data Index: 5440349 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.8060. Min Act: -0.1700
Data Index: 3068950 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.7748. Min Act: -0.1700
Data Index: 845594 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.6498. Min Act: -0.1700
Data Index: 4178718 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.6498. Min Act: -0.1700
Data Index: 3158485 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.6185. Min Act: -0.1700
Data Index: 6433857 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.6185. Min Act: -0.1700
Data Index: 6910256 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5873. Min Act: -0.1700
Data Index: 8703861 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5873. Min Act: -0.1700
Data Index: 261482 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5560. Min Act: -0.1700
Data Index: 2096270 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5248. Min Act: -0.1700
Data Index: 2234431 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5248. Min Act: -0.1700
Data Index: 7179930 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4935. Min Act: -0.1700
Data Index: 2335379 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5248. Min Act: -0.1700
Data Index: 3651857 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.5248. Min Act: -0.1700
Data Index: 2335381 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4935. Min Act: -0.1700
Data Index: 192536 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9935. Min Range: -5.9935
Max Act: 5.4623. Min Act: -0.1700
Data Index: 2177528 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19