Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0217. Min Range: -6.0217
Max Act: 6.0217. Min Act: -0.1700
Data Index: 239295 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.8342. Min Act: -0.1700
Data Index: 788390 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.7717. Min Act: -0.1700
Data Index: 7811820 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.7404. Min Act: -0.1700
Data Index: 7670695 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6779. Min Act: -0.1700
Data Index: 401047 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6467. Min Act: -0.1700
Data Index: 297454 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6467. Min Act: -0.1700
Data Index: 6791676 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6467. Min Act: -0.1700
Data Index: 2985272 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6467. Min Act: -0.1700
Data Index: 6393325 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6467. Min Act: -0.1700
Data Index: 2678375 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6467. Min Act: -0.1700
Data Index: 7581498 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6154. Min Act: -0.1700
Data Index: 5354251 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6154. Min Act: -0.1700
Data Index: 2944994 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6154. Min Act: -0.1700
Data Index: 8579906 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.6154. Min Act: -0.1700
Data Index: 8368780 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.5842. Min Act: -0.1700
Data Index: 6714997 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.5842. Min Act: -0.1700
Data Index: 6084667 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.5529. Min Act: -0.1700
Data Index: 2209038 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.5529. Min Act: -0.1700
Data Index: 2708565 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0217. Min Range: -6.0217
Max Act: 5.5217. Min Act: -0.1700
Data Index: 5945627 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19