Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5415 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1544. Min Range: -7.1544
Max Act: 7.1544. Min Act: -0.1700
Data Index: 4932016 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1544. Min Range: -7.1544
Max Act: 7.1544. Min Act: -0.1700
Data Index: 2547478 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1544. Min Range: -7.1544
Max Act: 7.1232. Min Act: -0.1700
Data Index: 3841430 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.9669. Min Act: -0.1700
Data Index: 8474160 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.9357. Min Act: -0.1700
Data Index: 6704374 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.9044. Min Act: -0.1700
Data Index: 3447375 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.8419. Min Act: -0.1700
Data Index: 3431512 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.8107. Min Act: -0.1700
Data Index: 748853 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.6857. Min Act: -0.1700
Data Index: 2641934 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.5919. Min Act: -0.1700
Data Index: 7257357 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.5919. Min Act: -0.1700
Data Index: 2118087 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.5607. Min Act: -0.1700
Data Index: 8307192 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4982. Min Act: -0.1700
Data Index: 97453 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4669. Min Act: -0.1700
Data Index: 4028153 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4669. Min Act: -0.1700
Data Index: 6432145 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4357. Min Act: -0.1700
Data Index: 1614517 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4357. Min Act: -0.1700
Data Index: 5813121 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4357. Min Act: -0.1700
Data Index: 5371163 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4357. Min Act: -0.1700
Data Index: 5761645 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1544. Min Range: -7.1544
Max Act: 6.4357. Min Act: -0.1700
Data Index: 3255533 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19