Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4400 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3560. Min Range: -9.3560
Max Act: 9.3560. Min Act: -0.1700
Data Index: 4245184 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3560. Min Range: -9.3560
Max Act: 9.2935. Min Act: -0.1700
Data Index: 3265986 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3560. Min Range: -9.3560
Max Act: 9.2935. Min Act: -0.1700
Data Index: 3020002 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3560. Min Range: -9.3560
Max Act: 9.1060. Min Act: -0.1700
Data Index: 2913881 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3560. Min Range: -9.3560
Max Act: 9.1685. Min Act: -0.1700
Data Index: 8096648 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3560. Min Range: -9.3560
Max Act: 9.1060. Min Act: -0.1700
Data Index: 7387240 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.9810. Min Act: -0.1700
Data Index: 8053847 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.9810. Min Act: -0.1700
Data Index: 7742091 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.9185. Min Act: -0.1700
Data Index: 5969652 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.7935. Min Act: -0.1700
Data Index: 5254000 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.7935. Min Act: -0.1700
Data Index: 2992002 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.7310. Min Act: -0.1700
Data Index: 6964243 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.7310. Min Act: -0.1700
Data Index: 1435982 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.6685. Min Act: -0.1700
Data Index: 723756 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.6060. Min Act: -0.1700
Data Index: 4507884 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.5435. Min Act: -0.1700
Data Index: 8640009 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.4810. Min Act: -0.1700
Data Index: 5007070 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.4810. Min Act: -0.1700
Data Index: 7903802 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.4810. Min Act: -0.1700
Data Index: 6647905 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3560. Min Range: -9.3560
Max Act: 8.4185. Min Act: -0.1700
Data Index: 6143080 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19