Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1002 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4530. Min Range: -8.4530
Max Act: 8.4530. Min Act: -0.1700
Data Index: 5202143 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4530. Min Range: -8.4530
Max Act: 8.2655. Min Act: -0.1700
Data Index: 746190 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4530. Min Range: -8.4530
Max Act: 8.0780. Min Act: -0.1700
Data Index: 4224581 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.9530. Min Act: -0.1700
Data Index: 2109498 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.9530. Min Act: -0.1700
Data Index: 4360843 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.9530. Min Act: -0.1700
Data Index: 1760148 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.8905. Min Act: -0.1700
Data Index: 7086564 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.9530. Min Act: -0.1700
Data Index: 6023698 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.8905. Min Act: -0.1700
Data Index: 4298092 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.8280. Min Act: -0.1700
Data Index: 7471514 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.8280. Min Act: -0.1700
Data Index: 7496121 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.7655. Min Act: -0.1700
Data Index: 1485069 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.7655. Min Act: -0.1700
Data Index: 7091237 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.7655. Min Act: -0.1700
Data Index: 720491 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.7030. Min Act: -0.1700
Data Index: 1465416 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.7030. Min Act: -0.1700
Data Index: 4834704 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.6405. Min Act: -0.1700
Data Index: 6280774 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.6405. Min Act: -0.1700
Data Index: 5074614 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.6405. Min Act: -0.1700
Data Index: 4940614 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4530. Min Range: -8.4530
Max Act: 7.6405. Min Act: -0.1700
Data Index: 2717807 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19