Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2555 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0724. Min Range: -6.0724
Max Act: 6.0724. Min Act: -0.1700
Data Index: 1850211 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.8536. Min Act: -0.1700
Data Index: 3407220 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.6661. Min Act: -0.1700
Data Index: 7075168 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.6349. Min Act: -0.1700
Data Index: 1049415 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.6349. Min Act: -0.1700
Data Index: 3810148 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.6349. Min Act: -0.1700
Data Index: 5827129 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5724. Min Act: -0.1700
Data Index: 4385377 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5724. Min Act: -0.1700
Data Index: 3746836 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5411. Min Act: -0.1700
Data Index: 3890504 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5411. Min Act: -0.1700
Data Index: 3903989 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5411. Min Act: -0.1700
Data Index: 49724 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5411. Min Act: -0.1700
Data Index: 5252992 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5724. Min Act: -0.1700
Data Index: 4523442 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.4786. Min Act: -0.1700
Data Index: 8690975 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5099. Min Act: -0.1700
Data Index: 2432620 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.5099. Min Act: -0.1700
Data Index: 6087861 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.4786. Min Act: -0.1700
Data Index: 2269247 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.4786. Min Act: -0.1700
Data Index: 8061260 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.4474. Min Act: -0.1700
Data Index: 1142310 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0724. Min Range: -6.0724
Max Act: 5.4474. Min Act: -0.1700
Data Index: 8068870 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19