Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0865. Min Range: -5.0865
Max Act: 5.0865. Min Act: -0.1700
Data Index: 3496979 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.9927. Min Act: -0.1700
Data Index: 8778523 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.9302. Min Act: -0.1700
Data Index: 70403 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8990. Min Act: -0.1700
Data Index: 8767038 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8990. Min Act: -0.1700
Data Index: 8738761 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8990. Min Act: -0.1700
Data Index: 7590288 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8990. Min Act: -0.1700
Data Index: 605448 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8990. Min Act: -0.1700
Data Index: 2309557 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8677. Min Act: -0.1700
Data Index: 6766406 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8677. Min Act: -0.1700
Data Index: 3501230 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8052. Min Act: -0.1700
Data Index: 4978250 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8365. Min Act: -0.1700
Data Index: 7991577 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8052. Min Act: -0.1700
Data Index: 6712671 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.7740. Min Act: -0.1700
Data Index: 5344216 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.7740. Min Act: -0.1700
Data Index: 3796544 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.8052. Min Act: -0.1700
Data Index: 6388910 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.7115. Min Act: -0.1700
Data Index: 2571066 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.7427. Min Act: -0.1700
Data Index: 2406757 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.7115. Min Act: -0.1700
Data Index: 1466727 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0865. Min Range: -5.0865
Max Act: 4.7115. Min Act: -0.1700
Data Index: 5820590 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19