Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 869 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1219. Min Range: -7.1219
Max Act: 7.1219. Min Act: -0.1700
Data Index: 4090586 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1219. Min Range: -7.1219
Max Act: 6.5281. Min Act: -0.1700
Data Index: 7077820 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1219. Min Range: -7.1219
Max Act: 6.1531. Min Act: -0.1700
Data Index: 5863210 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1219. Min Range: -7.1219
Max Act: 6.0594. Min Act: -0.1700
Data Index: 5275077 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1219. Min Range: -7.1219
Max Act: 6.1219. Min Act: -0.1700
Data Index: 3951651 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1219. Min Range: -7.1219
Max Act: 6.0594. Min Act: -0.1700
Data Index: 6020795 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.8719. Min Act: -0.1700
Data Index: 1102388 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.8094. Min Act: -0.1700
Data Index: 3326789 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.8094. Min Act: -0.1700
Data Index: 4658513 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.8094. Min Act: -0.1700
Data Index: 8723972 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.7469. Min Act: -0.1700
Data Index: 6212829 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.6844. Min Act: -0.1700
Data Index: 3882435 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.7469. Min Act: -0.1700
Data Index: 512059 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.7469. Min Act: -0.1700
Data Index: 4542848 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.6531. Min Act: -0.1700
Data Index: 6808868 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.6844. Min Act: -0.1700
Data Index: 3600225 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.6219. Min Act: -0.1700
Data Index: 1057739 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.6219. Min Act: -0.1700
Data Index: 6908349 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.5594. Min Act: -0.1700
Data Index: 3428578 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1219. Min Range: -7.1219
Max Act: 5.5594. Min Act: -0.1700
Data Index: 5108193 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19