Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4465 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1561. Min Range: -5.1561
Max Act: 5.1561. Min Act: -0.1700
Data Index: 1113403 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1561. Min Range: -5.1561
Max Act: 5.0623. Min Act: -0.1700
Data Index: 8569990 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.9686. Min Act: -0.1700
Data Index: 8647251 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.9998. Min Act: -0.1700
Data Index: 7350214 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.9061. Min Act: -0.1700
Data Index: 1113404 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.9061. Min Act: -0.1700
Data Index: 5470377 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.9061. Min Act: -0.1700
Data Index: 547712 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.8748. Min Act: -0.1700
Data Index: 1721175 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.9061. Min Act: -0.1700
Data Index: 5317128 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.8123. Min Act: -0.1700
Data Index: 2033500 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.8436. Min Act: -0.1700
Data Index: 267384 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.8436. Min Act: -0.1700
Data Index: 2259558 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.8123. Min Act: -0.1700
Data Index: 5203831 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.7498. Min Act: -0.1700
Data Index: 6359903 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.7498. Min Act: -0.1700
Data Index: 6623490 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.7498. Min Act: -0.1700
Data Index: 318140 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.7498. Min Act: -0.1700
Data Index: 2358667 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.7186. Min Act: -0.1700
Data Index: 7410903 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.7186. Min Act: -0.1700
Data Index: 4815979 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1561. Min Range: -5.1561
Max Act: 4.7186. Min Act: -0.1700
Data Index: 4521875 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #19