Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2657. Min Range: -7.2657
Max Act: 7.2657. Min Act: -0.1700
Data Index: 3063079 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2657. Min Range: -7.2657
Max Act: 7.2032. Min Act: -0.1700
Data Index: 2258191 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2657. Min Range: -7.2657
Max Act: 7.0157. Min Act: -0.1700
Data Index: 3775923 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2657. Min Range: -7.2657
Max Act: 7.0469. Min Act: -0.1700
Data Index: 8213591 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2657. Min Range: -7.2657
Max Act: 7.0469. Min Act: -0.1700
Data Index: 1291453 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.9532. Min Act: -0.1700
Data Index: 6292420 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.9532. Min Act: -0.1700
Data Index: 2079184 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.9219. Min Act: -0.1700
Data Index: 4174361 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.9219. Min Act: -0.1700
Data Index: 1353961 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.8907. Min Act: -0.1700
Data Index: 1236339 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.8907. Min Act: -0.1700
Data Index: 5471203 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.8594. Min Act: -0.1700
Data Index: 3423730 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.8594. Min Act: -0.1700
Data Index: 7753110 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.8282. Min Act: -0.1700
Data Index: 1660971 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.8282. Min Act: -0.1700
Data Index: 6218551 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.7657. Min Act: -0.1700
Data Index: 3176395 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.7969. Min Act: -0.1700
Data Index: 1323337 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.7969. Min Act: -0.1700
Data Index: 4790126 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.7969. Min Act: -0.1700
Data Index: 3576448 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2657. Min Range: -7.2657
Max Act: 6.7969. Min Act: -0.1700
Data Index: 3009362 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #19