Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2261 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.6450. Min Act: -0.1700
Data Index: 784423 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.5825. Min Act: -0.1700
Data Index: 2059792 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.4575. Min Act: -0.1700
Data Index: 615242 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.2700. Min Act: -0.1700
Data Index: 4325970 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.1450. Min Act: -0.1700
Data Index: 4309374 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.1450. Min Act: -0.1700
Data Index: 6289686 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.0825. Min Act: -0.1700
Data Index: 3524901 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.1450. Min Act: -0.1700
Data Index: 1553567 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.0825. Min Act: -0.1700
Data Index: 3723241 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.0825. Min Act: -0.1700
Data Index: 711772 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.0200. Min Act: -0.1700
Data Index: 4981766 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.0200. Min Act: -0.1700
Data Index: 3144192 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6450. Min Range: -9.6450
Max Act: 9.0200. Min Act: -0.1700
Data Index: 5971889 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6450. Min Range: -9.6450
Max Act: 8.8950. Min Act: -0.1700
Data Index: 6862969 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6450. Min Range: -9.6450
Max Act: 8.8950. Min Act: -0.1700
Data Index: 4665153 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6450. Min Range: -9.6450
Max Act: 8.8950. Min Act: -0.1700
Data Index: 4690699 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6450. Min Range: -9.6450
Max Act: 8.8950. Min Act: -0.1700
Data Index: 7067816 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6450. Min Range: -9.6450
Max Act: 8.8325. Min Act: -0.1700
Data Index: 3972900 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6450. Min Range: -9.6450
Max Act: 8.8325. Min Act: -0.1700
Data Index: 3965066 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6450. Min Range: -9.6450
Max Act: 8.8325. Min Act: -0.1700
Data Index: 615240 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19