Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3126 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.1295. Min Act: -0.1700
Data Index: 4162575 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0670. Min Act: -0.1700
Data Index: 8144012 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 4155874 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9420. Min Act: -0.1700
Data Index: 4698563 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9733. Min Act: -0.1700
Data Index: 1869303 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9420. Min Act: -0.1700
Data Index: 8502061 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8795. Min Act: -0.1700
Data Index: 7158187 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 4803454 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 1697623 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8170. Min Act: -0.1700
Data Index: 1636651 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7858. Min Act: -0.1700
Data Index: 4614872 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7858. Min Act: -0.1700
Data Index: 6575330 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7858. Min Act: -0.1700
Data Index: 4962697 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7233. Min Act: -0.1700
Data Index: 1770008 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7233. Min Act: -0.1700
Data Index: 1736935 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.7233. Min Act: -0.1700
Data Index: 1923492 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6920. Min Act: -0.1700
Data Index: 6845526 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6608. Min Act: -0.1700
Data Index: 6382132 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6920. Min Act: -0.1700
Data Index: 1605786 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.6295. Min Act: -0.1700
Data Index: 2938063 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19