Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.6408. Min Act: -0.1700
Data Index: 723093 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.3908. Min Act: -0.1700
Data Index: 8068237 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.3595. Min Act: -0.1700
Data Index: 4528798 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.3283. Min Act: -0.1700
Data Index: 4660 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.3283. Min Act: -0.1700
Data Index: 2766611 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.3595. Min Act: -0.1700
Data Index: 1717272 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.2658. Min Act: -0.1700
Data Index: 3808968 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.2345. Min Act: -0.1700
Data Index: 7077143 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.2345. Min Act: -0.1700
Data Index: 413647 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.2033. Min Act: -0.1700
Data Index: 4130198 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.2033. Min Act: -0.1700
Data Index: 4340783 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.1720. Min Act: -0.1700
Data Index: 2866205 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.1408. Min Act: -0.1700
Data Index: 8463685 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.1408. Min Act: -0.1700
Data Index: 6369996 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.1095. Min Act: -0.1700
Data Index: 4204941 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.1408. Min Act: -0.1700
Data Index: 150846 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.0783. Min Act: -0.1700
Data Index: 1037781 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.0470. Min Act: -0.1700
Data Index: 4144409 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.0470. Min Act: -0.1700
Data Index: 6743778 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6408. Min Range: -5.6408
Max Act: 5.0470. Min Act: -0.1700
Data Index: 5649217 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19