Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0570. Min Range: -6.0570
Max Act: 6.0570. Min Act: -0.1700
Data Index: 127063 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.9633. Min Act: -0.1700
Data Index: 1540894 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.9008. Min Act: -0.1700
Data Index: 7763286 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.9008. Min Act: -0.1700
Data Index: 3549857 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.8070. Min Act: -0.1700
Data Index: 6660680 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.8383. Min Act: -0.1700
Data Index: 7003446 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.8070. Min Act: -0.1700
Data Index: 5064865 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.7445. Min Act: -0.1700
Data Index: 7003447 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.7445. Min Act: -0.1700
Data Index: 6989879 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.7133. Min Act: -0.1700
Data Index: 6676651 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6508. Min Act: -0.1700
Data Index: 1810424 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6820. Min Act: -0.1700
Data Index: 2550277 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6820. Min Act: -0.1700
Data Index: 407088 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6820. Min Act: -0.1700
Data Index: 2454723 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6508. Min Act: -0.1700
Data Index: 7372822 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6195. Min Act: -0.1700
Data Index: 2792580 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6508. Min Act: -0.1700
Data Index: 7722844 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.6195. Min Act: -0.1700
Data Index: 5450894 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.5883. Min Act: -0.1700
Data Index: 2926167 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0570. Min Range: -6.0570
Max Act: 5.5883. Min Act: -0.1700
Data Index: 4110463 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19