Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5958 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.5244. Min Act: -0.1700
Data Index: 5359175 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.3681. Min Act: -0.1700
Data Index: 3690943 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.3056. Min Act: -0.1700
Data Index: 7376300 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.3056. Min Act: -0.1700
Data Index: 4221301 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.2744. Min Act: -0.1700
Data Index: 1544608 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.2744. Min Act: -0.1700
Data Index: 898380 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.2431. Min Act: -0.1700
Data Index: 7376302 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.2431. Min Act: -0.1700
Data Index: 2213331 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.2119. Min Act: -0.1700
Data Index: 5325034 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1806. Min Act: -0.1700
Data Index: 4288238 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1806. Min Act: -0.1700
Data Index: 4104970 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1806. Min Act: -0.1700
Data Index: 180503 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1806. Min Act: -0.1700
Data Index: 241404 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1494. Min Act: -0.1700
Data Index: 5261102 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1494. Min Act: -0.1700
Data Index: 774397 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1181. Min Act: -0.1700
Data Index: 1730766 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1181. Min Act: -0.1700
Data Index: 6174149 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1181. Min Act: -0.1700
Data Index: 6700887 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.1181. Min Act: -0.1700
Data Index: 3664535 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5244. Min Range: -4.5244
Max Act: 4.0869. Min Act: -0.1700
Data Index: 4789004 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19