Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1585. Min Range: -7.1585
Max Act: 7.1585. Min Act: -0.1700
Data Index: 3119425 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1585. Min Range: -7.1585
Max Act: 7.0023. Min Act: -0.1700
Data Index: 7132851 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.8773. Min Act: -0.1700
Data Index: 2685751 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.8148. Min Act: -0.1700
Data Index: 2132059 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.7835. Min Act: -0.1700
Data Index: 6052374 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.8148. Min Act: -0.1700
Data Index: 1936411 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.6585. Min Act: -0.1700
Data Index: 7743348 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.5648. Min Act: -0.1700
Data Index: 5218615 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.5960. Min Act: -0.1700
Data Index: 4958706 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.5023. Min Act: -0.1700
Data Index: 6815299 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.5023. Min Act: -0.1700
Data Index: 5732001 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.4710. Min Act: -0.1700
Data Index: 197328 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.4398. Min Act: -0.1700
Data Index: 6866242 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.4398. Min Act: -0.1700
Data Index: 8186292 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.3773. Min Act: -0.1700
Data Index: 8282901 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.4085. Min Act: -0.1700
Data Index: 5748412 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.4085. Min Act: -0.1700
Data Index: 653316 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.3773. Min Act: -0.1700
Data Index: 387756 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.3773. Min Act: -0.1700
Data Index: 2618257 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1585. Min Range: -7.1585
Max Act: 6.3773. Min Act: -0.1700
Data Index: 2419901 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19