Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3200 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.4091. Min Act: -0.1700
Data Index: 4376187 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.3779. Min Act: -0.1700
Data Index: 4376185 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.3466. Min Act: -0.1700
Data Index: 4944387 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.3466. Min Act: -0.1700
Data Index: 4376186 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.3466. Min Act: -0.1700
Data Index: 5103886 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.2216. Min Act: -0.1700
Data Index: 1630136 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1904. Min Act: -0.1700
Data Index: 3761253 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1904. Min Act: -0.1700
Data Index: 7076542 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1904. Min Act: -0.1700
Data Index: 6411011 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1904. Min Act: -0.1700
Data Index: 4376184 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1904. Min Act: -0.1700
Data Index: 4460237 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1591. Min Act: -0.1700
Data Index: 3761254 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1591. Min Act: -0.1700
Data Index: 6411012 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1591. Min Act: -0.1700
Data Index: 6411013 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1591. Min Act: -0.1700
Data Index: 7076540 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7076539 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.1279. Min Act: -0.1700
Data Index: 7076543 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.0654. Min Act: -0.1700
Data Index: 6475918 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.0654. Min Act: -0.1700
Data Index: 6594192 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4091. Min Range: -6.4091
Max Act: 6.0654. Min Act: -0.1700
Data Index: 2002855 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19