Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 204 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.5814. Min Act: -0.1700
Data Index: 54247 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.5189. Min Act: -0.1700
Data Index: 4155746 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.3314. Min Act: -0.1700
Data Index: 6417299 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.2377. Min Act: -0.1700
Data Index: 5014248 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.2377. Min Act: -0.1700
Data Index: 7404817 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.2064. Min Act: -0.1700
Data Index: 2631638 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.1439. Min Act: -0.1700
Data Index: 3351213 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0814. Min Act: -0.1700
Data Index: 8074882 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.1127. Min Act: -0.1700
Data Index: 1927478 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.1127. Min Act: -0.1700
Data Index: 2522122 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0814. Min Act: -0.1700
Data Index: 4027286 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0814. Min Act: -0.1700
Data Index: 5623733 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0814. Min Act: -0.1700
Data Index: 1823715 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0814. Min Act: -0.1700
Data Index: 4164842 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0814. Min Act: -0.1700
Data Index: 8382622 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0502. Min Act: -0.1700
Data Index: 2494684 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0502. Min Act: -0.1700
Data Index: 4610235 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0502. Min Act: -0.1700
Data Index: 8116976 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0502. Min Act: -0.1700
Data Index: 3742663 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5814. Min Range: -6.5814
Max Act: 6.0502. Min Act: -0.1700
Data Index: 12874 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19