Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5834 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.4483. Min Act: -0.1700
Data Index: 8586834 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.2608. Min Act: -0.1700
Data Index: 142823 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.1670. Min Act: -0.1700
Data Index: 6648976 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.1358. Min Act: -0.1700
Data Index: 8061445 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.1045. Min Act: -0.1700
Data Index: 3100117 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0733. Min Act: -0.1700
Data Index: 3100116 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0733. Min Act: -0.1700
Data Index: 7699344 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0420. Min Act: -0.1700
Data Index: 774963 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0420. Min Act: -0.1700
Data Index: 7699346 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0420. Min Act: -0.1700
Data Index: 2620400 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0420. Min Act: -0.1700
Data Index: 905563 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0108. Min Act: -0.1700
Data Index: 1582823 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0108. Min Act: -0.1700
Data Index: 1175239 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4483. Min Range: -6.4483
Max Act: 6.0108. Min Act: -0.1700
Data Index: 2837826 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4483. Min Range: -6.4483
Max Act: 5.9483. Min Act: -0.1700
Data Index: 2470256 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4483. Min Range: -6.4483
Max Act: 5.9795. Min Act: -0.1700
Data Index: 5261357 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4483. Min Range: -6.4483
Max Act: 5.9795. Min Act: -0.1700
Data Index: 6745785 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4483. Min Range: -6.4483
Max Act: 5.9795. Min Act: -0.1700
Data Index: 5768865 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4483. Min Range: -6.4483
Max Act: 5.9795. Min Act: -0.1700
Data Index: 3775432 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4483. Min Range: -6.4483
Max Act: 5.9483. Min Act: -0.1700
Data Index: 5508427 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19