Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3994 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.1262. Min Act: -0.1700
Data Index: 7963997 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0949. Min Act: -0.1700
Data Index: 5111058 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0949. Min Act: -0.1700
Data Index: 6395314 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.1262. Min Act: -0.1700
Data Index: 5279060 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.1574. Min Act: -0.1700
Data Index: 5645992 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0012. Min Act: -0.1700
Data Index: 4024621 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0324. Min Act: -0.1700
Data Index: 4569766 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0012. Min Act: -0.1700
Data Index: 7112105 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.9699. Min Act: -0.1700
Data Index: 5828368 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0012. Min Act: -0.1700
Data Index: 2897409 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0012. Min Act: -0.1700
Data Index: 6590536 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0012. Min Act: -0.1700
Data Index: 1804788 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1574. Min Range: -8.1574
Max Act: 8.0012. Min Act: -0.1700
Data Index: 4106078 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.9699. Min Act: -0.1700
Data Index: 6302715 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.8449. Min Act: -0.1700
Data Index: 8142048 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.9074. Min Act: -0.1700
Data Index: 8403414 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.9387. Min Act: -0.1700
Data Index: 3400830 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.9699. Min Act: -0.1700
Data Index: 4187204 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.9387. Min Act: -0.1700
Data Index: 8142047 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1574. Min Range: -8.1574
Max Act: 7.9699. Min Act: -0.1700
Data Index: 495354 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19