Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.6127. Min Act: -0.1700
Data Index: 98526 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.4877. Min Act: -0.1700
Data Index: 4986255 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.4877. Min Act: -0.1700
Data Index: 4714029 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.4565. Min Act: -0.1700
Data Index: 1394818 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.3940. Min Act: -0.1700
Data Index: 6626105 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.3940. Min Act: -0.1700
Data Index: 8800632 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.3627. Min Act: -0.1700
Data Index: 7318320 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.3315. Min Act: -0.1700
Data Index: 4108646 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.3315. Min Act: -0.1700
Data Index: 1294918 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2690. Min Act: -0.1700
Data Index: 8012770 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.3002. Min Act: -0.1700
Data Index: 6396939 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2690. Min Act: -0.1700
Data Index: 6626943 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2690. Min Act: -0.1700
Data Index: 3730376 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2377. Min Act: -0.1700
Data Index: 1316471 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2065. Min Act: -0.1700
Data Index: 1318104 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2065. Min Act: -0.1700
Data Index: 8686692 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2065. Min Act: -0.1700
Data Index: 4556859 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2065. Min Act: -0.1700
Data Index: 6118681 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.2065. Min Act: -0.1700
Data Index: 8295560 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6127. Min Range: -6.6127
Max Act: 6.1752. Min Act: -0.1700
Data Index: 7879708 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19