Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.5837. Min Act: -0.1700
Data Index: 3974451 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.4587. Min Act: -0.1700
Data Index: 6422947 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.4587. Min Act: -0.1700
Data Index: 3384668 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.3962. Min Act: -0.1700
Data Index: 6043135 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.3962. Min Act: -0.1700
Data Index: 1029220 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.3337. Min Act: -0.1700
Data Index: 2138351 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.3337. Min Act: -0.1700
Data Index: 536666 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2712. Min Act: -0.1700
Data Index: 1574701 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2712. Min Act: -0.1700
Data Index: 8320891 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2712. Min Act: -0.1700
Data Index: 4324047 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2712. Min Act: -0.1700
Data Index: 6979371 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2087. Min Act: -0.1700
Data Index: 5942157 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2087. Min Act: -0.1700
Data Index: 336815 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2087. Min Act: -0.1700
Data Index: 7313107 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2087. Min Act: -0.1700
Data Index: 2738247 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.1462. Min Act: -0.1700
Data Index: 4231853 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.2087. Min Act: -0.1700
Data Index: 5088074 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.1462. Min Act: -0.1700
Data Index: 1595278 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.0837. Min Act: -0.1700
Data Index: 1873390 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5837. Min Range: -9.5837
Max Act: 9.1462. Min Act: -0.1700
Data Index: 1370415 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19