Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2392 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.4051. Min Act: -0.1700
Data Index: 3082140 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.2488. Min Act: -0.1700
Data Index: 2049087 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.1551. Min Act: -0.1700
Data Index: 1655493 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.0926. Min Act: -0.1700
Data Index: 567488 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.0613. Min Act: -0.1700
Data Index: 5404166 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.0300. Min Act: -0.1700
Data Index: 5179774 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.0613. Min Act: -0.1700
Data Index: 347686 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.0300. Min Act: -0.1700
Data Index: 6138009 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.0300. Min Act: -0.1700
Data Index: 4067719 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4051. Min Range: -4.4051
Max Act: 4.0300. Min Act: -0.1700
Data Index: 737767 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9675. Min Act: -0.1700
Data Index: 518179 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9675. Min Act: -0.1700
Data Index: 2228364 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9988. Min Act: -0.1700
Data Index: 2077296 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9988. Min Act: -0.1700
Data Index: 4479792 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9988. Min Act: -0.1700
Data Index: 5944976 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9675. Min Act: -0.1700
Data Index: 6204160 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9675. Min Act: -0.1700
Data Index: 8451062 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9363. Min Act: -0.1700
Data Index: 6696525 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9363. Min Act: -0.1700
Data Index: 6537684 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4051. Min Range: -4.4051
Max Act: 3.9363. Min Act: -0.1700
Data Index: 8068959 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19