Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6342 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.4333. Min Act: -0.1700
Data Index: 366963 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.4333. Min Act: -0.1700
Data Index: 1111608 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.4333. Min Act: -0.1700
Data Index: 5856112 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.3395. Min Act: -0.1700
Data Index: 8570633 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.3708. Min Act: -0.1700
Data Index: 6715925 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.2770. Min Act: -0.1700
Data Index: 3685034 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.2770. Min Act: -0.1700
Data Index: 2719444 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.2770. Min Act: -0.1700
Data Index: 5988081 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.2145. Min Act: -0.1700
Data Index: 8468658 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1833. Min Act: -0.1700
Data Index: 6480261 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1833. Min Act: -0.1700
Data Index: 4098229 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1833. Min Act: -0.1700
Data Index: 7824814 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1833. Min Act: -0.1700
Data Index: 552079 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1520. Min Act: -0.1700
Data Index: 2908255 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1520. Min Act: -0.1700
Data Index: 1997247 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1208. Min Act: -0.1700
Data Index: 7724422 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1208. Min Act: -0.1700
Data Index: 7849086 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.1208. Min Act: -0.1700
Data Index: 7133209 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.0895. Min Act: -0.1700
Data Index: 2914603 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4333. Min Range: -5.4333
Max Act: 5.0895. Min Act: -0.1700
Data Index: 269302 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19