Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6301 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.9344. Min Act: -0.1699
Data Index: 7523957 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.9028. Min Act: -0.1700
Data Index: 6289116 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8551. Min Act: -0.1700
Data Index: 1336044 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8392. Min Act: -0.1700
Data Index: 8145736 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8392. Min Act: -0.1700
Data Index: 99101 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8392. Min Act: -0.1700
Data Index: 3780352 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8392. Min Act: -0.1700
Data Index: 1256767 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8074. Min Act: -0.1700
Data Index: 8464341 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8233. Min Act: -0.1700
Data Index: 8379442 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8233. Min Act: -0.1700
Data Index: 7138951 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8074. Min Act: -0.1700
Data Index: 4135599 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.8074. Min Act: -0.1700
Data Index: 2129746 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7915. Min Act: -0.1700
Data Index: 929624 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7915. Min Act: -0.1700
Data Index: 4631108 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7756. Min Act: -0.1700
Data Index: 1284632 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7596. Min Act: -0.1700
Data Index: 1443534 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7756. Min Act: -0.1700
Data Index: 5565896 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7596. Min Act: -0.1700
Data Index: 4393972 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7756. Min Act: -0.1700
Data Index: 8494043 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9344. Min Range: -2.9344
Max Act: 2.7756. Min Act: -0.1700
Data Index: 1002126 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19