Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.5389. Min Act: -0.1700
Data Index: 5045184 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.5389. Min Act: -0.1700
Data Index: 1761380 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.4764. Min Act: -0.1700
Data Index: 2479824 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.4451. Min Act: -0.1700
Data Index: 2918229 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.4139. Min Act: -0.1700
Data Index: 4763805 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.4139. Min Act: -0.1700
Data Index: 6547240 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.3201. Min Act: -0.1700
Data Index: 8817954 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.2264. Min Act: -0.1700
Data Index: 2834236 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.2264. Min Act: -0.1700
Data Index: 6968095 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1951. Min Act: -0.1700
Data Index: 6459269 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.2264. Min Act: -0.1700
Data Index: 4105080 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.2264. Min Act: -0.1700
Data Index: 7691481 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1951. Min Act: -0.1700
Data Index: 1280258 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1951. Min Act: -0.1700
Data Index: 4123055 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1951. Min Act: -0.1700
Data Index: 3515549 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1951. Min Act: -0.1700
Data Index: 1545182 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1639. Min Act: -0.1700
Data Index: 112740 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1014. Min Act: -0.1700
Data Index: 7674236 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1326. Min Act: -0.1700
Data Index: 6840863 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5389. Min Range: -4.5389
Max Act: 4.1014. Min Act: -0.1700
Data Index: 2865523 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19