Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1217 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.3243. Min Act: -0.1700
Data Index: 6231007 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.3243. Min Act: -0.1700
Data Index: 2063048 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.2931. Min Act: -0.1700
Data Index: 6104394 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.2931. Min Act: -0.1700
Data Index: 5830094 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.2618. Min Act: -0.1700
Data Index: 1426980 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1993. Min Act: -0.1700
Data Index: 492606 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1056. Min Act: -0.1700
Data Index: 1328935 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1368. Min Act: -0.1700
Data Index: 8214843 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1368. Min Act: -0.1700
Data Index: 5963565 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1368. Min Act: -0.1700
Data Index: 7111454 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1368. Min Act: -0.1700
Data Index: 1780154 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1056. Min Act: -0.1700
Data Index: 8078158 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.1056. Min Act: -0.1700
Data Index: 4223159 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.0431. Min Act: -0.1700
Data Index: 238577 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.0743. Min Act: -0.1700
Data Index: 4971164 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.0743. Min Act: -0.1700
Data Index: 160436 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3243. Min Range: -5.3243
Max Act: 4.9806. Min Act: -0.1700
Data Index: 6348564 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.0431. Min Act: -0.1700
Data Index: 110150 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.0118. Min Act: -0.1700
Data Index: 1239451 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3243. Min Range: -5.3243
Max Act: 5.0118. Min Act: -0.1700
Data Index: 4392453 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19