Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4928 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1574. Min Range: -6.1574
Max Act: 6.1574. Min Act: -0.1700
Data Index: 6536929 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1574. Min Range: -6.1574
Max Act: 6.1261. Min Act: -0.1700
Data Index: 5832309 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1574. Min Range: -6.1574
Max Act: 6.0324. Min Act: -0.1700
Data Index: 6627438 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1574. Min Range: -6.1574
Max Act: 6.0011. Min Act: -0.1700
Data Index: 3683068 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1574. Min Range: -6.1574
Max Act: 6.0011. Min Act: -0.1700
Data Index: 8388543 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9699. Min Act: -0.1700
Data Index: 6080093 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9699. Min Act: -0.1700
Data Index: 2224302 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9699. Min Act: -0.1700
Data Index: 3407390 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9386. Min Act: -0.1700
Data Index: 3460413 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9386. Min Act: -0.1700
Data Index: 8334825 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9386. Min Act: -0.1700
Data Index: 3944012 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9074. Min Act: -0.1700
Data Index: 8412702 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.9074. Min Act: -0.1700
Data Index: 2383236 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.8761. Min Act: -0.1700
Data Index: 2305311 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.8761. Min Act: -0.1700
Data Index: 1175593 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.8761. Min Act: -0.1700
Data Index: 5770969 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.8761. Min Act: -0.1700
Data Index: 988160 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.8449. Min Act: -0.1700
Data Index: 5148021 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.8449. Min Act: -0.1700
Data Index: 3377121 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1574. Min Range: -6.1574
Max Act: 5.8449. Min Act: -0.1700
Data Index: 4120747 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19