Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1363. Min Range: -5.1363
Max Act: 5.1363. Min Act: -0.1700
Data Index: 1933913 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1363. Min Range: -5.1363
Max Act: 5.1363. Min Act: -0.1700
Data Index: 2983195 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.9800. Min Act: -0.1700
Data Index: 3340990 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.9175. Min Act: -0.1700
Data Index: 3304050 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8863. Min Act: -0.1700
Data Index: 276553 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8863. Min Act: -0.1699
Data Index: 4445673 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8863. Min Act: -0.1700
Data Index: 4292225 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8863. Min Act: -0.1700
Data Index: 2338368 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8863. Min Act: -0.1700
Data Index: 870981 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8550. Min Act: -0.1700
Data Index: 1532290 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8550. Min Act: -0.1700
Data Index: 7601896 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8550. Min Act: -0.1700
Data Index: 3692205 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8550. Min Act: -0.1700
Data Index: 1784434 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 703261 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 2992131 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 2900035 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 2840547 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 2804121 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 1625786 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7925. Min Act: -0.1700
Data Index: 3347538 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19