Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4710 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.9574. Min Act: -0.1700
Data Index: 6883362 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.7699. Min Act: -0.1700
Data Index: 3657684 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.7387. Min Act: -0.1700
Data Index: 8339788 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.6762. Min Act: -0.1700
Data Index: 6848356 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.5824. Min Act: -0.1700
Data Index: 5902373 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.5824. Min Act: -0.1700
Data Index: 7642638 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.5824. Min Act: -0.1700
Data Index: 1179146 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.5512. Min Act: -0.1700
Data Index: 5824112 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.5512. Min Act: -0.1700
Data Index: 1432187 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.5199. Min Act: -0.1700
Data Index: 1723339 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.5199. Min Act: -0.1700
Data Index: 7967201 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4887. Min Act: -0.1700
Data Index: 5546224 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4574. Min Act: -0.1700
Data Index: 7976309 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4887. Min Act: -0.1700
Data Index: 3318311 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4887. Min Act: -0.1700
Data Index: 3071636 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4887. Min Act: -0.1700
Data Index: 3724151 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4887. Min Act: -0.1700
Data Index: 3018874 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4887. Min Act: -0.1700
Data Index: 7449121 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4887. Min Act: -0.1700
Data Index: 6582784 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9574. Min Range: -4.9574
Max Act: 4.4574. Min Act: -0.1700
Data Index: 2132229 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19