Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4049. Min Range: -6.4049
Max Act: 6.4049. Min Act: -0.1700
Data Index: 4004601 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4049. Min Range: -6.4049
Max Act: 6.2799. Min Act: -0.1700
Data Index: 3342444 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.9986. Min Act: -0.1700
Data Index: 7549547 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.9361. Min Act: -0.1700
Data Index: 826910 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.9049. Min Act: -0.1700
Data Index: 7617084 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.8424. Min Act: -0.1700
Data Index: 1624193 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.8111. Min Act: -0.1700
Data Index: 1845279 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.8111. Min Act: -0.1700
Data Index: 7029733 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.7799. Min Act: -0.1700
Data Index: 3982167 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.7486. Min Act: -0.1700
Data Index: 1689955 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.7486. Min Act: -0.1700
Data Index: 3171848 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.7174. Min Act: -0.1700
Data Index: 4460692 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.7174. Min Act: -0.1700
Data Index: 1610897 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.6861. Min Act: -0.1700
Data Index: 4822852 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.6861. Min Act: -0.1700
Data Index: 7713846 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.6236. Min Act: -0.1700
Data Index: 7185505 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.6861. Min Act: -0.1700
Data Index: 7484771 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.6549. Min Act: -0.1700
Data Index: 6643963 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.6549. Min Act: -0.1700
Data Index: 5963352 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4049. Min Range: -6.4049
Max Act: 5.6549. Min Act: -0.1700
Data Index: 8124440 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19