Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.5708. Min Act: -0.1700
Data Index: 2907693 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.3833. Min Act: -0.1700
Data Index: 3647338 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.4458. Min Act: -0.1700
Data Index: 4958429 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.3833. Min Act: -0.1700
Data Index: 7142351 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.3208. Min Act: -0.1700
Data Index: 7044195 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.2583. Min Act: -0.1700
Data Index: 7044194 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.2896. Min Act: -0.1700
Data Index: 1654165 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.1958. Min Act: -0.1700
Data Index: 7047221 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.1646. Min Act: -0.1700
Data Index: 8507841 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.1021. Min Act: -0.1700
Data Index: 2831472 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.1021. Min Act: -0.1700
Data Index: 2251888 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0708. Min Act: -0.1700
Data Index: 4415297 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0708. Min Act: -0.1700
Data Index: 6897006 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0396. Min Act: -0.1700
Data Index: 4138283 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0708. Min Act: -0.1700
Data Index: 4919156 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0396. Min Act: -0.1700
Data Index: 8786380 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0396. Min Act: -0.1700
Data Index: 7142352 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0396. Min Act: -0.1700
Data Index: 4958428 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0396. Min Act: -0.1700
Data Index: 7470066 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5708. Min Range: -5.5708
Max Act: 5.0396. Min Act: -0.1700
Data Index: 6087781 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19