Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3281 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0705. Min Range: -2.0705
Max Act: 2.0705. Min Act: -0.1700
Data Index: 3000329 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0705. Min Range: -2.0705
Max Act: 2.0031. Min Act: -0.1700
Data Index: 1919017 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9862. Min Act: -0.1700
Data Index: 7800958 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9693. Min Act: -0.1700
Data Index: 7721638 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9693. Min Act: -0.1700
Data Index: 4619880 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9693. Min Act: -0.1700
Data Index: 4345820 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9523. Min Act: -0.1700
Data Index: 4623085 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9693. Min Act: -0.1700
Data Index: 6096107 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9523. Min Act: -0.1700
Data Index: 5384453 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9353. Min Act: -0.1700
Data Index: 33230 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9523. Min Act: -0.1700
Data Index: 1005515 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9013. Min Act: -0.1700
Data Index: 280905 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9183. Min Act: -0.1700
Data Index: 519516 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9013. Min Act: -0.1700
Data Index: 8799592 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9353. Min Act: -0.1700
Data Index: 8201293 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9183. Min Act: -0.1700
Data Index: 1982903 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9013. Min Act: -0.1700
Data Index: 997410 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9353. Min Act: -0.1700
Data Index: 7601713 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.9013. Min Act: -0.1700
Data Index: 843978 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0705. Min Range: -2.0705
Max Act: 1.8842. Min Act: -0.1700
Data Index: 6219652 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19