Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2118 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0778. Min Range: -5.0778
Max Act: 5.0778. Min Act: -0.1700
Data Index: 4285071 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0778. Min Range: -5.0778
Max Act: 5.0778. Min Act: -0.1700
Data Index: 6840272 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0778. Min Range: -5.0778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 2241083 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0778. Min Range: -5.0778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 8720534 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0778. Min Range: -5.0778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 3009597 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0778. Min Range: -5.0778
Max Act: 5.0153. Min Act: -0.1700
Data Index: 1342296 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.9215. Min Act: -0.1700
Data Index: 4244124 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.8903. Min Act: -0.1700
Data Index: 720883 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.8903. Min Act: -0.1700
Data Index: 357983 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.9215. Min Act: -0.1700
Data Index: 2028807 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.8903. Min Act: -0.1700
Data Index: 279078 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.8590. Min Act: -0.1700
Data Index: 5486910 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.8590. Min Act: -0.1700
Data Index: 3490715 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.7965. Min Act: -0.1700
Data Index: 4103503 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.7965. Min Act: -0.1700
Data Index: 7738086 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.7965. Min Act: -0.1700
Data Index: 8523711 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.7653. Min Act: -0.1700
Data Index: 7947422 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.7965. Min Act: -0.1700
Data Index: 2701002 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.7653. Min Act: -0.1700
Data Index: 7006847 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0778. Min Range: -5.0778
Max Act: 4.7653. Min Act: -0.1700
Data Index: 7530484 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #19