Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2334 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.4118. Min Act: -0.1700
Data Index: 247544 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.3493. Min Act: -0.1700
Data Index: 4619714 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.3180. Min Act: -0.1700
Data Index: 8158312 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.2868. Min Act: -0.1700
Data Index: 7919869 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.2868. Min Act: -0.1700
Data Index: 4790039 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.2555. Min Act: -0.1700
Data Index: 2786270 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.2243. Min Act: -0.1700
Data Index: 1790762 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.2555. Min Act: -0.1700
Data Index: 2944124 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.1930. Min Act: -0.1700
Data Index: 2468507 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.1930. Min Act: -0.1700
Data Index: 3058337 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.1305. Min Act: -0.1700
Data Index: 3709311 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.1305. Min Act: -0.1700
Data Index: 1077549 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.1618. Min Act: -0.1700
Data Index: 4347463 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.0993. Min Act: -0.1700
Data Index: 3058336 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.1305. Min Act: -0.1700
Data Index: 1230856 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.0680. Min Act: -0.1700
Data Index: 2816185 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.0993. Min Act: -0.1700
Data Index: 5219083 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.0993. Min Act: -0.1700
Data Index: 5591401 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.0368. Min Act: -0.1700
Data Index: 3058332 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4118. Min Range: -5.4118
Max Act: 5.0680. Min Act: -0.1700
Data Index: 4063102 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19