Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3679 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1976. Min Range: -7.1976
Max Act: 7.1976. Min Act: -0.1700
Data Index: 4293919 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1976. Min Range: -7.1976
Max Act: 7.1663. Min Act: -0.1700
Data Index: 499092 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1976. Min Range: -7.1976
Max Act: 7.0726. Min Act: -0.1700
Data Index: 7446332 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1976. Min Range: -7.1976
Max Act: 7.0101. Min Act: -0.1700
Data Index: 1513892 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.9476. Min Act: -0.1700
Data Index: 6103221 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.8538. Min Act: -0.1700
Data Index: 3631291 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.8851. Min Act: -0.1700
Data Index: 7872243 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.8851. Min Act: -0.1700
Data Index: 5245566 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.8226. Min Act: -0.1700
Data Index: 4594224 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.8226. Min Act: -0.1700
Data Index: 270457 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.7601. Min Act: -0.1700
Data Index: 556056 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.7288. Min Act: -0.1700
Data Index: 6903865 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.7288. Min Act: -0.1700
Data Index: 8393001 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.6976. Min Act: -0.1700
Data Index: 3195792 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.6976. Min Act: -0.1700
Data Index: 5904230 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.6663. Min Act: -0.1700
Data Index: 3168805 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.6663. Min Act: -0.1700
Data Index: 4032827 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.6663. Min Act: -0.1700
Data Index: 4738603 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.6663. Min Act: -0.1700
Data Index: 5613670 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1976. Min Range: -7.1976
Max Act: 6.6976. Min Act: -0.1700
Data Index: 7951749 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19