Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2167 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.7466. Min Act: -0.1700
Data Index: 4948407 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.7466. Min Act: -0.1700
Data Index: 7927563 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6666. Min Act: -0.1700
Data Index: 3715329 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6986. Min Act: -0.1700
Data Index: 750410 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6506. Min Act: -0.1700
Data Index: 5367228 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6666. Min Act: -0.1700
Data Index: 8383542 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6666. Min Act: -0.1700
Data Index: 6792449 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6184. Min Act: -0.1700
Data Index: 1038244 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6184. Min Act: -0.1700
Data Index: 1086236 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6506. Min Act: -0.1700
Data Index: 48094 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6184. Min Act: -0.1700
Data Index: 3814405 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6184. Min Act: -0.1700
Data Index: 5319941 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6024. Min Act: -0.1700
Data Index: 108969 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.5701. Min Act: -0.1700
Data Index: 6783731 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6024. Min Act: -0.1700
Data Index: 7249042 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.5863. Min Act: -0.1700
Data Index: 1635418 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.6024. Min Act: -0.1700
Data Index: 8548960 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.5863. Min Act: -0.1700
Data Index: 3696401 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.5863. Min Act: -0.1700
Data Index: 5688182 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7466. Min Range: -2.7466
Max Act: 2.5701. Min Act: -0.1700
Data Index: 2557547 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19