Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3075 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.4958. Min Act: -0.1700
Data Index: 2741438 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3704. Min Act: -0.1700
Data Index: 8564039 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3547. Min Act: -0.1700
Data Index: 8065111 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3390. Min Act: -0.1700
Data Index: 3038705 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3390. Min Act: -0.1700
Data Index: 1832915 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3390. Min Act: -0.1700
Data Index: 4734319 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3390. Min Act: -0.1700
Data Index: 3231594 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3233. Min Act: -0.1700
Data Index: 3444183 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3076. Min Act: -0.1700
Data Index: 3296623 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.3233. Min Act: -0.1700
Data Index: 7547790 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2919. Min Act: -0.1700
Data Index: 3452550 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2919. Min Act: -0.1700
Data Index: 5914392 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2762. Min Act: -0.1700
Data Index: 3123288 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2605. Min Act: -0.1700
Data Index: 1617176 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2605. Min Act: -0.1700
Data Index: 6671129 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2605. Min Act: -0.1700
Data Index: 7675003 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2605. Min Act: -0.1700
Data Index: 582018 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2448. Min Act: -0.1700
Data Index: 3824195 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2448. Min Act: -0.1700
Data Index: 1021453 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4958. Min Range: -3.4958
Max Act: 3.2291. Min Act: -0.1700
Data Index: 7416046 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19