Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0597. Min Range: -9.0597
Max Act: 9.0597. Min Act: -0.1700
Data Index: 8565261 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.6222. Min Act: -0.1700
Data Index: 2872998 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.4347. Min Act: -0.1700
Data Index: 1392482 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.3097. Min Act: -0.1700
Data Index: 7433881 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.3097. Min Act: -0.1700
Data Index: 3313902 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.3097. Min Act: -0.1700
Data Index: 8447869 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.2472. Min Act: -0.1700
Data Index: 5390556 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1847. Min Act: -0.1700
Data Index: 6527214 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 7782318 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1847. Min Act: -0.1700
Data Index: 8501160 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 2082122 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 3659606 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 1164337 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 2659901 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 5263853 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 5270290 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.0597. Min Act: -0.1700
Data Index: 6474565 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.1222. Min Act: -0.1700
Data Index: 8037979 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.0597. Min Act: -0.1700
Data Index: 3835938 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0597. Min Range: -9.0597
Max Act: 8.0597. Min Act: -0.1700
Data Index: 8028360 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19