Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2517 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1835. Min Range: -5.1835
Max Act: 5.1835. Min Act: -0.1700
Data Index: 7544888 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1835. Min Range: -5.1835
Max Act: 5.1210. Min Act: -0.1700
Data Index: 903067 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1835. Min Range: -5.1835
Max Act: 5.0897. Min Act: -0.1700
Data Index: 6017701 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.9960. Min Act: -0.1700
Data Index: 6417505 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.9960. Min Act: -0.1700
Data Index: 8201779 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.9647. Min Act: -0.1700
Data Index: 7566037 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.9335. Min Act: -0.1700
Data Index: 7840440 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.9335. Min Act: -0.1700
Data Index: 551525 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.9022. Min Act: -0.1700
Data Index: 7411971 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8710. Min Act: -0.1700
Data Index: 1483355 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8397. Min Act: -0.1700
Data Index: 7122194 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8397. Min Act: -0.1700
Data Index: 1827742 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8397. Min Act: -0.1700
Data Index: 200586 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8397. Min Act: -0.1700
Data Index: 5371284 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8397. Min Act: -0.1700
Data Index: 8400909 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8397. Min Act: -0.1700
Data Index: 2289401 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8085. Min Act: -0.1700
Data Index: 2924986 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8085. Min Act: -0.1700
Data Index: 8377870 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8085. Min Act: -0.1700
Data Index: 5774185 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1835. Min Range: -5.1835
Max Act: 4.8085. Min Act: -0.1700
Data Index: 5781175 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19