Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.2487. Min Act: -0.1700
Data Index: 7335571 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.1862. Min Act: -0.1700
Data Index: 1373310 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.0925. Min Act: -0.1700
Data Index: 2370066 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.0612. Min Act: -0.1700
Data Index: 6720101 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.0612. Min Act: -0.1700
Data Index: 2364336 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9987. Min Act: -0.1700
Data Index: 7335576 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2487. Min Range: -7.2487
Max Act: 7.0612. Min Act: -0.1700
Data Index: 2364334 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9675. Min Act: -0.1700
Data Index: 6720097 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9362. Min Act: -0.1700
Data Index: 2364340 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9362. Min Act: -0.1700
Data Index: 8430695 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9050. Min Act: -0.1700
Data Index: 2188209 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9050. Min Act: -0.1700
Data Index: 6001795 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8737. Min Act: -0.1700
Data Index: 5178853 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.9050. Min Act: -0.1700
Data Index: 6738074 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8425. Min Act: -0.1700
Data Index: 5178852 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8737. Min Act: -0.1700
Data Index: 8518056 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8425. Min Act: -0.1700
Data Index: 6001796 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8425. Min Act: -0.1700
Data Index: 2188210 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8737. Min Act: -0.1700
Data Index: 2364344 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2487. Min Range: -7.2487
Max Act: 6.8425. Min Act: -0.1700
Data Index: 1373306 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19