Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2690 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1883. Min Range: -8.1883
Max Act: 8.1883. Min Act: -0.1700
Data Index: 8717439 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.8133. Min Act: -0.1700
Data Index: 8412908 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.6883. Min Act: -0.1700
Data Index: 3521184 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.5008. Min Act: -0.1700
Data Index: 1676457 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.5008. Min Act: -0.1700
Data Index: 5997198 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 3949564 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 5446058 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 640942 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 4227236 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.4070. Min Act: -0.1700
Data Index: 237860 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.3758. Min Act: -0.1700
Data Index: 2459409 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.3445. Min Act: -0.1700
Data Index: 1780971 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.3133. Min Act: -0.1700
Data Index: 8498731 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.3445. Min Act: -0.1700
Data Index: 5430574 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.2820. Min Act: -0.1700
Data Index: 3339470 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.2820. Min Act: -0.1700
Data Index: 3407074 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.2508. Min Act: -0.1700
Data Index: 4821071 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.2508. Min Act: -0.1700
Data Index: 4787861 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.2508. Min Act: -0.1700
Data Index: 2810179 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1883. Min Range: -8.1883
Max Act: 7.2508. Min Act: -0.1700
Data Index: 8367606 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19