Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4358 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6819. Min Range: -8.6819
Max Act: 8.6819. Min Act: -0.1700
Data Index: 1576750 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6819. Min Range: -8.6819
Max Act: 8.3694. Min Act: -0.1700
Data Index: 2911297 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6819. Min Range: -8.6819
Max Act: 8.2444. Min Act: -0.1700
Data Index: 8717108 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6819. Min Range: -8.6819
Max Act: 8.1194. Min Act: -0.1700
Data Index: 5144825 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6819. Min Range: -8.6819
Max Act: 8.1194. Min Act: -0.1700
Data Index: 1228786 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6819. Min Range: -8.6819
Max Act: 8.1194. Min Act: -0.1700
Data Index: 271328 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.9944. Min Act: -0.1700
Data Index: 3406774 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.9944. Min Act: -0.1700
Data Index: 5248407 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.9944. Min Act: -0.1700
Data Index: 5732040 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.9319. Min Act: -0.1700
Data Index: 3647464 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.8069. Min Act: -0.1700
Data Index: 642177 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.8694. Min Act: -0.1700
Data Index: 7756546 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.8069. Min Act: -0.1700
Data Index: 2059487 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.8069. Min Act: -0.1700
Data Index: 1512021 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.8069. Min Act: -0.1700
Data Index: 2569776 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.8069. Min Act: -0.1700
Data Index: 3017060 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.6819. Min Act: -0.1700
Data Index: 6319098 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.6819. Min Act: -0.1700
Data Index: 8566257 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.6819. Min Act: -0.1700
Data Index: 8436363 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6819. Min Range: -8.6819
Max Act: 7.6819. Min Act: -0.1700
Data Index: 1441396 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19