Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1563 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1408. Min Range: -6.1408
Max Act: 6.1408. Min Act: -0.1700
Data Index: 1451245 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.7970. Min Act: -0.1700
Data Index: 4325492 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.8283. Min Act: -0.1700
Data Index: 5555618 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.7658. Min Act: -0.1700
Data Index: 8250037 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.7345. Min Act: -0.1700
Data Index: 6720709 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.6408. Min Act: -0.1700
Data Index: 1966819 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.6408. Min Act: -0.1700
Data Index: 6275367 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.6408. Min Act: -0.1700
Data Index: 4297887 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.6095. Min Act: -0.1700
Data Index: 7842462 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.6408. Min Act: -0.1700
Data Index: 6679710 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.6095. Min Act: -0.1700
Data Index: 2278174 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.5470. Min Act: -0.1700
Data Index: 3334115 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.6095. Min Act: -0.1700
Data Index: 6705872 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.5470. Min Act: -0.1700
Data Index: 4492213 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.5470. Min Act: -0.1700
Data Index: 3603077 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.5470. Min Act: -0.1700
Data Index: 8738669 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.5470. Min Act: -0.1700
Data Index: 6807378 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.5158. Min Act: -0.1700
Data Index: 7959842 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.5158. Min Act: -0.1700
Data Index: 3741266 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1408. Min Range: -6.1408
Max Act: 5.4845. Min Act: -0.1700
Data Index: 3837553 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19