Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.6237. Min Act: -0.1700
Data Index: 1483965 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.4675. Min Act: -0.1700
Data Index: 2961122 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.3737. Min Act: -0.1700
Data Index: 4701341 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.2800. Min Act: -0.1700
Data Index: 5165511 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.2175. Min Act: -0.1700
Data Index: 6330019 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.1862. Min Act: -0.1700
Data Index: 3217422 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.1550. Min Act: -0.1700
Data Index: 3388236 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.1237. Min Act: -0.1700
Data Index: 2762032 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.0612. Min Act: -0.1700
Data Index: 3601837 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.0925. Min Act: -0.1700
Data Index: 8198017 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.0612. Min Act: -0.1700
Data Index: 921655 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.0612. Min Act: -0.1700
Data Index: 493551 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.0925. Min Act: -0.1700
Data Index: 4564155 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6237. Min Range: -6.6237
Max Act: 6.0612. Min Act: -0.1700
Data Index: 4309170 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6237. Min Range: -6.6237
Max Act: 5.9987. Min Act: -0.1700
Data Index: 8599599 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6237. Min Range: -6.6237
Max Act: 5.9362. Min Act: -0.1700
Data Index: 6724159 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6237. Min Range: -6.6237
Max Act: 5.9362. Min Act: -0.1700
Data Index: 8575926 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6237. Min Range: -6.6237
Max Act: 5.9362. Min Act: -0.1700
Data Index: 2157701 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6237. Min Range: -6.6237
Max Act: 5.9050. Min Act: -0.1700
Data Index: 5018482 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6237. Min Range: -6.6237
Max Act: 5.9050. Min Act: -0.1700
Data Index: 6071783 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19