Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.6965. Min Act: -0.1700
Data Index: 691926 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.6652. Min Act: -0.1700
Data Index: 6667162 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.6027. Min Act: -0.1700
Data Index: 8163394 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.6340. Min Act: -0.1700
Data Index: 8674251 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.6027. Min Act: -0.1700
Data Index: 1145650 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.5715. Min Act: -0.1700
Data Index: 3273313 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.5715. Min Act: -0.1700
Data Index: 8521862 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.5715. Min Act: -0.1700
Data Index: 3594785 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.5402. Min Act: -0.1700
Data Index: 7581285 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.5402. Min Act: -0.1700
Data Index: 200701 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.5090. Min Act: -0.1700
Data Index: 1814935 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4777. Min Act: -0.1700
Data Index: 200702 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4777. Min Act: -0.1700
Data Index: 2194094 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4777. Min Act: -0.1700
Data Index: 8163395 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4777. Min Act: -0.1700
Data Index: 5545807 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4777. Min Act: -0.1700
Data Index: 1389445 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4777. Min Act: -0.1700
Data Index: 420737 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4465. Min Act: -0.1700
Data Index: 7479221 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4152. Min Act: -0.1700
Data Index: 866386 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6965. Min Range: -6.6965
Max Act: 6.4465. Min Act: -0.1700
Data Index: 7742808 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19