Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 345 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.9430. Min Act: -0.1700
Data Index: 7779962 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8919. Min Act: -0.1700
Data Index: 6253929 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8919. Min Act: -0.1700
Data Index: 7051795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 2401893 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8748. Min Act: -0.1700
Data Index: 1230599 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8748. Min Act: -0.1700
Data Index: 7329677 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 1861065 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 1487946 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 4333097 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 6062559 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 3648309 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 8791955 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8406. Min Act: -0.1700
Data Index: 1795796 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8406. Min Act: -0.1700
Data Index: 111412 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8234. Min Act: -0.1700
Data Index: 919417 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8406. Min Act: -0.1700
Data Index: 4441737 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8406. Min Act: -0.1700
Data Index: 5058374 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8406. Min Act: -0.1700
Data Index: 1795798 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8577. Min Act: -0.1700
Data Index: 354277 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9430. Min Range: -1.9430
Max Act: 1.8234. Min Act: -0.1700
Data Index: 6859270 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19