Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1102 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.3935. Min Act: -0.1700
Data Index: 7588282 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.3935. Min Act: -0.1700
Data Index: 746851 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.3623. Min Act: -0.1700
Data Index: 6616308 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.3623. Min Act: -0.1700
Data Index: 2007024 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.2998. Min Act: -0.1700
Data Index: 6581126 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.2060. Min Act: -0.1700
Data Index: 3787167 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.1748. Min Act: -0.1700
Data Index: 8442947 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.1748. Min Act: -0.1700
Data Index: 7689248 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.1435. Min Act: -0.1700
Data Index: 7802855 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.1435. Min Act: -0.1700
Data Index: 202771 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.1435. Min Act: -0.1700
Data Index: 5948087 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.1435. Min Act: -0.1700
Data Index: 7005788 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.1123. Min Act: -0.1700
Data Index: 5228184 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.0810. Min Act: -0.1700
Data Index: 583055 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.0498. Min Act: -0.1700
Data Index: 1655356 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3935. Min Range: -6.3935
Max Act: 6.0810. Min Act: -0.1700
Data Index: 7646950 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3935. Min Range: -6.3935
Max Act: 5.9873. Min Act: -0.1700
Data Index: 3170002 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3935. Min Range: -6.3935
Max Act: 5.9873. Min Act: -0.1700
Data Index: 7551309 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3935. Min Range: -6.3935
Max Act: 5.9873. Min Act: -0.1700
Data Index: 154632 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3935. Min Range: -6.3935
Max Act: 5.9560. Min Act: -0.1700
Data Index: 1120932 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19