Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2297 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.9468. Min Act: -0.1700
Data Index: 5156509 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.7281. Min Act: -0.1700
Data Index: 2600545 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.6968. Min Act: -0.1700
Data Index: 6438762 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.6656. Min Act: -0.1700
Data Index: 1730190 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.6343. Min Act: -0.1700
Data Index: 8529871 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.6031. Min Act: -0.1700
Data Index: 7929703 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.5718. Min Act: -0.1700
Data Index: 2381399 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.5093. Min Act: -0.1700
Data Index: 6993509 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.5093. Min Act: -0.1700
Data Index: 8075732 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.4781. Min Act: -0.1700
Data Index: 3303523 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.4468. Min Act: -0.1700
Data Index: 21344 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.4468. Min Act: -0.1700
Data Index: 7357514 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.4468. Min Act: -0.1700
Data Index: 8402822 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.4468. Min Act: -0.1700
Data Index: 7128132 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.4156. Min Act: -0.1700
Data Index: 8618288 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.3843. Min Act: -0.1700
Data Index: 6487118 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.3843. Min Act: -0.1700
Data Index: 3569401 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.3843. Min Act: -0.1700
Data Index: 1710448 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.3843. Min Act: -0.1700
Data Index: 361620 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9468. Min Range: -5.9468
Max Act: 5.3531. Min Act: -0.1700
Data Index: 5271896 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19