Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1362 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2696. Min Range: -8.2696
Max Act: 8.2696. Min Act: -0.1700
Data Index: 8434230 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.7383. Min Act: -0.1700
Data Index: 1877545 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.7383. Min Act: -0.1700
Data Index: 1278223 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.7071. Min Act: -0.1700
Data Index: 1040664 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6758. Min Act: -0.1700
Data Index: 7399206 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6758. Min Act: -0.1700
Data Index: 1659432 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6446. Min Act: -0.1700
Data Index: 3923809 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6446. Min Act: -0.1700
Data Index: 3315051 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6446. Min Act: -0.1700
Data Index: 147482 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6446. Min Act: -0.1700
Data Index: 4980547 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6133. Min Act: -0.1700
Data Index: 1049128 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.6133. Min Act: -0.1700
Data Index: 6911504 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.5821. Min Act: -0.1700
Data Index: 1248971 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.4883. Min Act: -0.1700
Data Index: 8043976 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.4883. Min Act: -0.1700
Data Index: 979407 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.4571. Min Act: -0.1700
Data Index: 1352852 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.4258. Min Act: -0.1700
Data Index: 3839448 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.3946. Min Act: -0.1700
Data Index: 1987193 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.4258. Min Act: -0.1700
Data Index: 6600860 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2696. Min Range: -8.2696
Max Act: 7.3946. Min Act: -0.1700
Data Index: 5975789 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19