Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3096 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.3081. Min Act: -0.1700
Data Index: 2950065 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.2456. Min Act: -0.1700
Data Index: 2887701 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.1831. Min Act: -0.1700
Data Index: 574957 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.1519. Min Act: -0.1700
Data Index: 3937305 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.1519. Min Act: -0.1700
Data Index: 408534 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.1206. Min Act: -0.1700
Data Index: 3194328 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.1206. Min Act: -0.1700
Data Index: 3132766 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 763616 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 2961452 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.0269. Min Act: -0.1700
Data Index: 5841655 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.0581. Min Act: -0.1700
Data Index: 6622341 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.0269. Min Act: -0.1700
Data Index: 7057508 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3081. Min Range: -6.3081
Max Act: 6.0269. Min Act: -0.1700
Data Index: 6523437 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3081. Min Range: -6.3081
Max Act: 5.9956. Min Act: -0.1700
Data Index: 3406189 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3081. Min Range: -6.3081
Max Act: 5.9956. Min Act: -0.1700
Data Index: 215162 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3081. Min Range: -6.3081
Max Act: 5.9956. Min Act: -0.1700
Data Index: 2701939 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3081. Min Range: -6.3081
Max Act: 5.9956. Min Act: -0.1700
Data Index: 532932 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3081. Min Range: -6.3081
Max Act: 5.9956. Min Act: -0.1700
Data Index: 4876928 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3081. Min Range: -6.3081
Max Act: 5.9644. Min Act: -0.1700
Data Index: 1881632 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3081. Min Range: -6.3081
Max Act: 5.9331. Min Act: -0.1700
Data Index: 6101322 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19