Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 264 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.6585. Min Range: -9.6585
Max Act: 9.6585. Min Act: -0.1700
Data Index: 2636559 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6585. Min Range: -9.6585
Max Act: 9.2210. Min Act: -0.1700
Data Index: 4130938 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6585. Min Range: -9.6585
Max Act: 9.2210. Min Act: -0.1700
Data Index: 6159578 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6585. Min Range: -9.6585
Max Act: 9.1585. Min Act: -0.1700
Data Index: 8211773 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6585. Min Range: -9.6585
Max Act: 9.0335. Min Act: -0.1700
Data Index: 4517637 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9710. Min Act: -0.1700
Data Index: 7294756 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9710. Min Act: -0.1700
Data Index: 6483128 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9710. Min Act: -0.1700
Data Index: 6365500 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 5110003 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 5152239 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9710. Min Act: -0.1700
Data Index: 5390201 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 474332 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 4032284 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 414582 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 7454465 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.8460. Min Act: -0.1700
Data Index: 7817492 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 830886 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.8460. Min Act: -0.1700
Data Index: 5829371 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.9085. Min Act: -0.1700
Data Index: 5624112 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6585. Min Range: -9.6585
Max Act: 8.8460. Min Act: -0.1700
Data Index: 7159783 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19