Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.5657. Min Act: -0.1700
Data Index: 7471702 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.3156. Min Act: -0.1700
Data Index: 4953742 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.2844. Min Act: -0.1700
Data Index: 394445 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.2844. Min Act: -0.1700
Data Index: 4974743 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.2844. Min Act: -0.1700
Data Index: 6370173 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.2531. Min Act: -0.1700
Data Index: 357152 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.2844. Min Act: -0.1700
Data Index: 4010383 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.2219. Min Act: -0.1700
Data Index: 2127845 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.2219. Min Act: -0.1700
Data Index: 8183121 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1594. Min Act: -0.1700
Data Index: 5989220 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1594. Min Act: -0.1700
Data Index: 4667233 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1594. Min Act: -0.1700
Data Index: 3283554 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1594. Min Act: -0.1700
Data Index: 8762333 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1594. Min Act: -0.1700
Data Index: 1834654 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1906. Min Act: -0.1700
Data Index: 3713419 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1594. Min Act: -0.1700
Data Index: 5586402 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.0969. Min Act: -0.1700
Data Index: 4837917 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1281. Min Act: -0.1700
Data Index: 7351502 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.1281. Min Act: -0.1700
Data Index: 3711562 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5657. Min Range: -4.5657
Max Act: 4.0969. Min Act: -0.1700
Data Index: 5009411 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19