Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6151 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.5700. Min Act: -0.1700
Data Index: 130940 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.5075. Min Act: -0.1700
Data Index: 2766923 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.4450. Min Act: -0.1700
Data Index: 2503238 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.3200. Min Act: -0.1700
Data Index: 1983015 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.3200. Min Act: -0.1700
Data Index: 7074897 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.3200. Min Act: -0.1700
Data Index: 4579756 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.2575. Min Act: -0.1700
Data Index: 3288815 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.2575. Min Act: -0.1700
Data Index: 5026560 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.1325. Min Act: -0.1700
Data Index: 6126295 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.1325. Min Act: -0.1700
Data Index: 2210322 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.0075. Min Act: -0.1700
Data Index: 3249171 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.9763. Min Act: -0.1700
Data Index: 6413548 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.9763. Min Act: -0.1700
Data Index: 5414388 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.9763. Min Act: -0.1700
Data Index: 6952470 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5700. Min Range: -8.5700
Max Act: 8.0075. Min Act: -0.1700
Data Index: 793037 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.9763. Min Act: -0.1700
Data Index: 3468090 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.9763. Min Act: -0.1700
Data Index: 7388992 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.9763. Min Act: -0.1700
Data Index: 770552 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.9450. Min Act: -0.1700
Data Index: 5678912 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5700. Min Range: -8.5700
Max Act: 7.8825. Min Act: -0.1700
Data Index: 7685784 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19