Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.6012. Min Act: -0.1700
Data Index: 46891 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.5699. Min Act: -0.1700
Data Index: 7782558 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.5387. Min Act: -0.1700
Data Index: 4002655 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.5387. Min Act: -0.1700
Data Index: 4331013 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4762. Min Act: -0.1700
Data Index: 8195160 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4762. Min Act: -0.1700
Data Index: 8295469 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4449. Min Act: -0.1700
Data Index: 7782563 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4449. Min Act: -0.1700
Data Index: 7735017 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4449. Min Act: -0.1700
Data Index: 162846 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 8457690 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 7472548 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 8215202 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1908904 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 1462897 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 5996270 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.4137. Min Act: -0.1700
Data Index: 4316759 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3824. Min Act: -0.1700
Data Index: 4355533 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3512. Min Act: -0.1700
Data Index: 4557276 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3824. Min Act: -0.1700
Data Index: 4557274 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6012. Min Range: -4.6012
Max Act: 4.3824. Min Act: -0.1700
Data Index: 7423392 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19