Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4006 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.4992. Min Act: -0.1700
Data Index: 8207682 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.4680. Min Act: -0.1700
Data Index: 7318637 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.4055. Min Act: -0.1700
Data Index: 762296 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.4055. Min Act: -0.1700
Data Index: 6095426 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3742. Min Act: -0.1700
Data Index: 4535280 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.4055. Min Act: -0.1700
Data Index: 2543915 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3742. Min Act: -0.1700
Data Index: 6601336 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.4055. Min Act: -0.1700
Data Index: 3358957 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3430. Min Act: -0.1700
Data Index: 4702981 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3117. Min Act: -0.1700
Data Index: 6601337 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3117. Min Act: -0.1700
Data Index: 1801468 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3117. Min Act: -0.1700
Data Index: 2561454 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3430. Min Act: -0.1700
Data Index: 1871634 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.2805. Min Act: -0.1700
Data Index: 5837918 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.2805. Min Act: -0.1700
Data Index: 6023019 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.3117. Min Act: -0.1700
Data Index: 4577150 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.2805. Min Act: -0.1700
Data Index: 2037677 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.2492. Min Act: -0.1700
Data Index: 5134360 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.2180. Min Act: -0.1700
Data Index: 4242914 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4992. Min Range: -4.4992
Max Act: 4.2180. Min Act: -0.1700
Data Index: 3898363 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19