Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4205. Min Range: -7.4205
Max Act: 7.4205. Min Act: -0.1700
Data Index: 7862854 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4205. Min Range: -7.4205
Max Act: 7.2642. Min Act: -0.1700
Data Index: 3057680 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.8892. Min Act: -0.1700
Data Index: 5252904 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.9205. Min Act: -0.1700
Data Index: 222732 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.8580. Min Act: -0.1700
Data Index: 7953744 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.8580. Min Act: -0.1700
Data Index: 4416379 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.7955. Min Act: -0.1700
Data Index: 3347064 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.7642. Min Act: -0.1700
Data Index: 3474104 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.7642. Min Act: -0.1700
Data Index: 2198545 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.7330. Min Act: -0.1700
Data Index: 8741578 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.7642. Min Act: -0.1700
Data Index: 334549 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.7330. Min Act: -0.1700
Data Index: 3759087 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.6392. Min Act: -0.1700
Data Index: 7232651 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.6705. Min Act: -0.1700
Data Index: 3732978 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.6392. Min Act: -0.1700
Data Index: 1002699 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.6080. Min Act: -0.1700
Data Index: 8290631 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.5455. Min Act: -0.1700
Data Index: 7484293 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.5455. Min Act: -0.1700
Data Index: 7117578 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.4517. Min Act: -0.1700
Data Index: 7223356 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4205. Min Range: -7.4205
Max Act: 6.4517. Min Act: -0.1700
Data Index: 2363362 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19