Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3956 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.3547. Min Act: -0.1700
Data Index: 3355 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.3235. Min Act: -0.1700
Data Index: 7802555 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2610. Min Act: -0.1700
Data Index: 6433355 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2610. Min Act: -0.1700
Data Index: 6832480 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2610. Min Act: -0.1700
Data Index: 5524824 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2610. Min Act: -0.1700
Data Index: 1055131 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2610. Min Act: -0.1700
Data Index: 4142155 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 43437 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 2098995 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 1544969 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 5831258 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 4205116 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 2631980 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 4810359 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 1229499 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 5210823 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 5755431 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.2297. Min Act: -0.1700
Data Index: 1332554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 3291005 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3547. Min Range: -5.3547
Max Act: 5.1985. Min Act: -0.1700
Data Index: 3343549 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19