Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.4848. Min Act: -0.1700
Data Index: 4122258 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.2661. Min Act: -0.1700
Data Index: 6275203 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.2661. Min Act: -0.1700
Data Index: 6627386 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.1723. Min Act: -0.1700
Data Index: 7278019 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.1098. Min Act: -0.1700
Data Index: 3794703 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.1098. Min Act: -0.1700
Data Index: 3926251 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0786. Min Act: -0.1700
Data Index: 5388558 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0786. Min Act: -0.1700
Data Index: 4568860 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0786. Min Act: -0.1700
Data Index: 6236506 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0786. Min Act: -0.1700
Data Index: 6366031 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0473. Min Act: -0.1700
Data Index: 3361854 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0473. Min Act: -0.1700
Data Index: 2264518 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0473. Min Act: -0.1700
Data Index: 4083098 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0161. Min Act: -0.1700
Data Index: 1754924 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0161. Min Act: -0.1700
Data Index: 4568838 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0161. Min Act: -0.1700
Data Index: 8022849 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0161. Min Act: -0.1700
Data Index: 1110091 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4848. Min Range: -5.4848
Max Act: 5.0161. Min Act: -0.1700
Data Index: 7228789 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4848. Min Range: -5.4848
Max Act: 4.9536. Min Act: -0.1700
Data Index: 2577455 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4848. Min Range: -5.4848
Max Act: 4.9536. Min Act: -0.1700
Data Index: 7277998 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19