Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.3830. Min Act: -0.1700
Data Index: 7496625 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.3517. Min Act: -0.1700
Data Index: 2957316 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.1017. Min Act: -0.1700
Data Index: 2422136 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.1330. Min Act: -0.1700
Data Index: 6630164 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.1017. Min Act: -0.1700
Data Index: 5326460 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.0705. Min Act: -0.1700
Data Index: 2015142 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.1017. Min Act: -0.1700
Data Index: 7107168 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9767. Min Act: -0.1700
Data Index: 4974271 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.0080. Min Act: -0.1700
Data Index: 8563614 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.0080. Min Act: -0.1700
Data Index: 6808113 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.0392. Min Act: -0.1700
Data Index: 5752681 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.0392. Min Act: -0.1700
Data Index: 7054533 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3830. Min Range: -6.3830
Max Act: 6.0080. Min Act: -0.1700
Data Index: 4985164 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9767. Min Act: -0.1700
Data Index: 2917179 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9142. Min Act: -0.1700
Data Index: 4344419 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9455. Min Act: -0.1700
Data Index: 865994 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9767. Min Act: -0.1700
Data Index: 3920508 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9455. Min Act: -0.1700
Data Index: 5082001 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9767. Min Act: -0.1700
Data Index: 6165632 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3830. Min Range: -6.3830
Max Act: 5.9455. Min Act: -0.1700
Data Index: 1359240 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19