Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5092 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.5148. Min Act: -0.1700
Data Index: 1281827 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.5148. Min Act: -0.1700
Data Index: 8768823 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.3273. Min Act: -0.1700
Data Index: 6446608 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.2648. Min Act: -0.1700
Data Index: 968883 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.2648. Min Act: -0.1700
Data Index: 2353469 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.2336. Min Act: -0.1700
Data Index: 1464556 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.2023. Min Act: -0.1700
Data Index: 984197 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.2023. Min Act: -0.1700
Data Index: 7142580 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.1711. Min Act: -0.1700
Data Index: 1460512 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.1398. Min Act: -0.1700
Data Index: 6370651 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.1398. Min Act: -0.1700
Data Index: 3419383 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.1086. Min Act: -0.1700
Data Index: 1056766 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0773. Min Act: -0.1700
Data Index: 5601480 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0461. Min Act: -0.1700
Data Index: 5089449 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0148. Min Act: -0.1700
Data Index: 1747925 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0773. Min Act: -0.1700
Data Index: 8185590 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0461. Min Act: -0.1700
Data Index: 7617770 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0148. Min Act: -0.1700
Data Index: 3802244 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0148. Min Act: -0.1700
Data Index: 219353 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5148. Min Range: -7.5148
Max Act: 7.0148. Min Act: -0.1700
Data Index: 2624106 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19