Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1373 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.4609. Min Act: -0.1700
Data Index: 8821006 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.4297. Min Act: -0.1700
Data Index: 3070772 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.3047. Min Act: -0.1700
Data Index: 7989173 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.2422. Min Act: -0.1700
Data Index: 2494803 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.2734. Min Act: -0.1700
Data Index: 4222299 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.2109. Min Act: -0.1700
Data Index: 8705993 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.2109. Min Act: -0.1700
Data Index: 1527198 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.2109. Min Act: -0.1700
Data Index: 5168873 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.1797. Min Act: -0.1700
Data Index: 3927617 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.1797. Min Act: -0.1700
Data Index: 4520453 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.1172. Min Act: -0.1700
Data Index: 1527191 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.1172. Min Act: -0.1700
Data Index: 5460372 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.1172. Min Act: -0.1700
Data Index: 7750586 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.0547. Min Act: -0.1700
Data Index: 4751696 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.0547. Min Act: -0.1700
Data Index: 3360404 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.0859. Min Act: -0.1700
Data Index: 3469234 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.0547. Min Act: -0.1700
Data Index: 7824211 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.0547. Min Act: -0.1700
Data Index: 7835901 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.0547. Min Act: -0.1700
Data Index: 3360091 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4609. Min Range: -5.4609
Max Act: 5.0547. Min Act: -0.1700
Data Index: 7750587 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19