Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2324 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.6305. Min Act: -0.1700
Data Index: 3498223 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5992. Min Act: -0.1700
Data Index: 6335131 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5680. Min Act: -0.1700
Data Index: 4262813 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5680. Min Act: -0.1700
Data Index: 5547446 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5680. Min Act: -0.1700
Data Index: 6724607 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5367. Min Act: -0.1700
Data Index: 4262809 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5680. Min Act: -0.1700
Data Index: 6498205 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5680. Min Act: -0.1700
Data Index: 2341225 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 2604861 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5367. Min Act: -0.1700
Data Index: 6888492 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5680. Min Act: -0.1700
Data Index: 7479703 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5367. Min Act: -0.1700
Data Index: 4514419 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 4644767 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 4347776 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 150374 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 1344375 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 5566282 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 7261065 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.4742. Min Act: -0.1700
Data Index: 6335256 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6305. Min Range: -4.6305
Max Act: 4.5055. Min Act: -0.1700
Data Index: 523245 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19