Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.6799. Min Act: -0.1700
Data Index: 801519 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.6799. Min Act: -0.1700
Data Index: 3099304 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.6486. Min Act: -0.1700
Data Index: 7352232 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.6174. Min Act: -0.1700
Data Index: 5085624 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.6174. Min Act: -0.1700
Data Index: 1807808 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.5861. Min Act: -0.1700
Data Index: 516573 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.6174. Min Act: -0.1700
Data Index: 6252152 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.5549. Min Act: -0.1700
Data Index: 7893240 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.5236. Min Act: -0.1700
Data Index: 4713765 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.5549. Min Act: -0.1700
Data Index: 2323774 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.5549. Min Act: -0.1700
Data Index: 8215632 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4924. Min Act: -0.1700
Data Index: 8605719 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 5388558 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 3017819 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 5480819 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 2984305 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 6892735 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 3583432 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 2274169 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6799. Min Range: -4.6799
Max Act: 4.4611. Min Act: -0.1700
Data Index: 4293258 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19