Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5410 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.6785. Min Act: -0.1700
Data Index: 6317253 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.6160. Min Act: -0.1700
Data Index: 7122941 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.5848. Min Act: -0.1700
Data Index: 624669 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.5848. Min Act: -0.1700
Data Index: 7582148 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.5223. Min Act: -0.1700
Data Index: 6081797 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.4910. Min Act: -0.1700
Data Index: 3477754 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.4910. Min Act: -0.1700
Data Index: 6269035 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.4598. Min Act: -0.1700
Data Index: 4969733 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.4285. Min Act: -0.1700
Data Index: 3014988 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.4285. Min Act: -0.1700
Data Index: 2688446 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3973. Min Act: -0.1700
Data Index: 4679988 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.4285. Min Act: -0.1700
Data Index: 4827148 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.4285. Min Act: -0.1700
Data Index: 6524549 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3660. Min Act: -0.1700
Data Index: 7976051 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3348. Min Act: -0.1700
Data Index: 3944973 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3035. Min Act: -0.1700
Data Index: 6257545 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3348. Min Act: -0.1700
Data Index: 518681 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3348. Min Act: -0.1700
Data Index: 4788386 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3348. Min Act: -0.1700
Data Index: 1727482 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6785. Min Range: -5.6785
Max Act: 5.3035. Min Act: -0.1700
Data Index: 5756250 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19