Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3309 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.5105. Min Act: -0.1700
Data Index: 3432874 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.4480. Min Act: -0.1700
Data Index: 1100331 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.4480. Min Act: -0.1700
Data Index: 2782934 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.4793. Min Act: -0.1700
Data Index: 1268307 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.4480. Min Act: -0.1700
Data Index: 6437321 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3855. Min Act: -0.1700
Data Index: 5041031 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3855. Min Act: -0.1700
Data Index: 4130932 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3855. Min Act: -0.1700
Data Index: 8800171 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3855. Min Act: -0.1700
Data Index: 4502058 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3543. Min Act: -0.1700
Data Index: 1586810 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3543. Min Act: -0.1700
Data Index: 1526570 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3543. Min Act: -0.1700
Data Index: 1761919 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3543. Min Act: -0.1700
Data Index: 5872152 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3543. Min Act: -0.1700
Data Index: 7947542 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.2918. Min Act: -0.1700
Data Index: 6619316 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3230. Min Act: -0.1700
Data Index: 2738673 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.2918. Min Act: -0.1700
Data Index: 1887977 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.3230. Min Act: -0.1700
Data Index: 1044785 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.2918. Min Act: -0.1700
Data Index: 3362127 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5105. Min Range: -5.5105
Max Act: 5.2918. Min Act: -0.1700
Data Index: 328934 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19