Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2240 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.7705. Min Act: -0.1700
Data Index: 4399962 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.7080. Min Act: -0.1700
Data Index: 104707 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.5830. Min Act: -0.1700
Data Index: 2614893 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.5517. Min Act: -0.1700
Data Index: 779581 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.5830. Min Act: -0.1700
Data Index: 4332466 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.4580. Min Act: -0.1700
Data Index: 4673537 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.4580. Min Act: -0.1700
Data Index: 7249245 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.4580. Min Act: -0.1700
Data Index: 4768934 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.3955. Min Act: -0.1700
Data Index: 4514987 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.3955. Min Act: -0.1700
Data Index: 6515942 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.3642. Min Act: -0.1700
Data Index: 8356968 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.3642. Min Act: -0.1700
Data Index: 6876713 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.3642. Min Act: -0.1700
Data Index: 7587459 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.3330. Min Act: -0.1700
Data Index: 7066285 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.2705. Min Act: -0.1700
Data Index: 6664256 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.2705. Min Act: -0.1700
Data Index: 3691672 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.3017. Min Act: -0.1700
Data Index: 1712235 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.2705. Min Act: -0.1700
Data Index: 6012576 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.2705. Min Act: -0.1700
Data Index: 1811078 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7705. Min Range: -7.7705
Max Act: 7.2392. Min Act: -0.1700
Data Index: 1021012 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19