Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 63 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9561. Min Act: -0.1700
Data Index: 609387 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9244. Min Act: -0.1700
Data Index: 3423203 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.9086. Min Act: -0.1700
Data Index: 8649845 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8927. Min Act: -0.1700
Data Index: 7634248 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8927. Min Act: -0.1700
Data Index: 393150 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8610. Min Act: -0.1700
Data Index: 350009 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8927. Min Act: -0.1700
Data Index: 7739695 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8610. Min Act: -0.1700
Data Index: 1989654 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8610. Min Act: -0.1700
Data Index: 143937 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8768. Min Act: -0.1700
Data Index: 547396 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8610. Min Act: -0.1700
Data Index: 2506959 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8610. Min Act: -0.1700
Data Index: 6370030 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8451. Min Act: -0.1700
Data Index: 1142279 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8451. Min Act: -0.1700
Data Index: 7515242 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8451. Min Act: -0.1700
Data Index: 6684163 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8451. Min Act: -0.1700
Data Index: 6684162 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8451. Min Act: -0.1700
Data Index: 3319289 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8451. Min Act: -0.1700
Data Index: 8250631 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8292. Min Act: -0.1700
Data Index: 4649274 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9561. Min Range: -2.9561
Max Act: 2.8610. Min Act: -0.1700
Data Index: 2468775 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19