Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1807 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5137. Min Range: -5.5137
Max Act: 5.5137. Min Act: -0.1700
Data Index: 6565797 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5137. Min Range: -5.5137
Max Act: 5.3262. Min Act: -0.1700
Data Index: 3152556 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5137. Min Range: -5.5137
Max Act: 5.2950. Min Act: -0.1700
Data Index: 5310464 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5137. Min Range: -5.5137
Max Act: 5.1075. Min Act: -0.1700
Data Index: 1220236 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5137. Min Range: -5.5137
Max Act: 5.0450. Min Act: -0.1700
Data Index: 3895106 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5137. Min Range: -5.5137
Max Act: 5.0137. Min Act: -0.1700
Data Index: 6565798 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.9825. Min Act: -0.1700
Data Index: 2716227 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.9512. Min Act: -0.1700
Data Index: 8774523 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.9200. Min Act: -0.1700
Data Index: 8562686 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.9200. Min Act: -0.1700
Data Index: 4031690 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8575. Min Act: -0.1700
Data Index: 5884997 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8887. Min Act: -0.1700
Data Index: 6240230 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8575. Min Act: -0.1700
Data Index: 6240227 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8262. Min Act: -0.1700
Data Index: 1531326 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8262. Min Act: -0.1700
Data Index: 5187806 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8262. Min Act: -0.1700
Data Index: 447361 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8262. Min Act: -0.1700
Data Index: 8154167 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8262. Min Act: -0.1700
Data Index: 4976318 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8262. Min Act: -0.1700
Data Index: 8170711 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5137. Min Range: -5.5137
Max Act: 4.8262. Min Act: -0.1700
Data Index: 8547101 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19