Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4386 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.4621. Min Act: -0.1700
Data Index: 2534635 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.3058. Min Act: -0.1700
Data Index: 6681768 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.2121. Min Act: -0.1699
Data Index: 1371936 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.1808. Min Act: -0.1700
Data Index: 2506027 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.1496. Min Act: -0.1700
Data Index: 5108515 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.1496. Min Act: -0.1700
Data Index: 5784616 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.1496. Min Act: -0.1700
Data Index: 2138579 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.0871. Min Act: -0.1700
Data Index: 8522656 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.1183. Min Act: -0.1700
Data Index: 1739898 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.0871. Min Act: -0.1700
Data Index: 246975 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.1183. Min Act: -0.1700
Data Index: 1307753 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.0558. Min Act: -0.1700
Data Index: 2145189 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.0246. Min Act: -0.1700
Data Index: 185665 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4621. Min Range: -7.4621
Max Act: 7.0246. Min Act: -0.1700
Data Index: 7077718 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4621. Min Range: -7.4621
Max Act: 6.9933. Min Act: -0.1700
Data Index: 6642417 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4621. Min Range: -7.4621
Max Act: 6.9933. Min Act: -0.1700
Data Index: 6496524 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4621. Min Range: -7.4621
Max Act: 6.9621. Min Act: -0.1700
Data Index: 3507775 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4621. Min Range: -7.4621
Max Act: 6.9933. Min Act: -0.1700
Data Index: 3749682 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4621. Min Range: -7.4621
Max Act: 6.9621. Min Act: -0.1700
Data Index: 6162059 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4621. Min Range: -7.4621
Max Act: 6.9308. Min Act: -0.1700
Data Index: 4738174 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19