Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.6577. Min Act: -0.1700
Data Index: 3038271 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.5639. Min Act: -0.1700
Data Index: 237603 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.5327. Min Act: -0.1700
Data Index: 4327426 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.5014. Min Act: -0.1700
Data Index: 5468462 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.5014. Min Act: -0.1700
Data Index: 4327425 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.4702. Min Act: -0.1700
Data Index: 2295999 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.3764. Min Act: -0.1700
Data Index: 5010361 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.3764. Min Act: -0.1700
Data Index: 5855762 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2827. Min Act: -0.1700
Data Index: 4193671 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2514. Min Act: -0.1700
Data Index: 6493714 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2514. Min Act: -0.1700
Data Index: 4025062 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2514. Min Act: -0.1700
Data Index: 172781 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2827. Min Act: -0.1700
Data Index: 2626869 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2202. Min Act: -0.1700
Data Index: 2853728 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2202. Min Act: -0.1700
Data Index: 2535210 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2202. Min Act: -0.1700
Data Index: 6898655 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.2202. Min Act: -0.1700
Data Index: 1711167 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.1889. Min Act: -0.1700
Data Index: 7544957 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.1889. Min Act: -0.1700
Data Index: 3934693 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6577. Min Range: -5.6577
Max Act: 5.1577. Min Act: -0.1700
Data Index: 668366 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19