Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5763 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.7350. Min Act: -0.1697
Data Index: 7177972 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6725. Min Act: -0.1699
Data Index: 6084254 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6725. Min Act: -0.1700
Data Index: 4949831 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 3360532 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 1416032 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 5852877 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6725. Min Act: -0.1700
Data Index: 1913537 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 1880306 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 5717527 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 5189249 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 4646466 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1699
Data Index: 1043072 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 3282176 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 1738075 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 278890 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 954298 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1677
Data Index: 3011316 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 376210 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 2939324 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7350. Min Range: -7.7350
Max Act: 7.6100. Min Act: -0.1700
Data Index: 545803 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19