Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6395 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.7004. Min Act: -0.1700
Data Index: 3196306 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.5442. Min Act: -0.1700
Data Index: 466116 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.5129. Min Act: -0.1700
Data Index: 7556276 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.5129. Min Act: -0.1700
Data Index: 1295809 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4817. Min Act: -0.1700
Data Index: 2981963 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4504. Min Act: -0.1700
Data Index: 8069255 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4192. Min Act: -0.1700
Data Index: 8490354 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4504. Min Act: -0.1700
Data Index: 3735801 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4192. Min Act: -0.1700
Data Index: 6285640 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4192. Min Act: -0.1700
Data Index: 6309226 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4192. Min Act: -0.1700
Data Index: 2393512 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3879. Min Act: -0.1700
Data Index: 5437120 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3875712 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3879. Min Act: -0.1700
Data Index: 7894693 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3879. Min Act: -0.1700
Data Index: 7548563 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3879. Min Act: -0.1699
Data Index: 1269049 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.4192. Min Act: -0.1700
Data Index: 6499328 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3879. Min Act: -0.1700
Data Index: 2393514 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3879. Min Act: -0.1700
Data Index: 3583873 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7004. Min Range: -5.7004
Max Act: 5.3567. Min Act: -0.1700
Data Index: 6469577 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19