Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1046 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2738. Min Range: -9.2738
Max Act: 9.2738. Min Act: -0.1700
Data Index: 396344 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.9613. Min Act: -0.1700
Data Index: 6697571 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.7738. Min Act: -0.1700
Data Index: 5424743 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.7738. Min Act: -0.1700
Data Index: 3659159 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.7113. Min Act: -0.1700
Data Index: 7826789 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.7113. Min Act: -0.1700
Data Index: 5164843 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.4613. Min Act: -0.1700
Data Index: 8588860 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3988. Min Act: -0.1700
Data Index: 8397590 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3988. Min Act: -0.1700
Data Index: 4875732 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3988. Min Act: -0.1700
Data Index: 4110346 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3988. Min Act: -0.1700
Data Index: 3594661 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3363. Min Act: -0.1700
Data Index: 4394862 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3363. Min Act: -0.1700
Data Index: 3130321 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3363. Min Act: -0.1700
Data Index: 4284201 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.3363. Min Act: -0.1700
Data Index: 7762929 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.2738. Min Act: -0.1700
Data Index: 259751 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.2738. Min Act: -0.1700
Data Index: 3904538 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.2738. Min Act: -0.1700
Data Index: 5424119 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.2738. Min Act: -0.1700
Data Index: 7635124 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2738. Min Range: -9.2738
Max Act: 8.2738. Min Act: -0.1700
Data Index: 7113377 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #19