Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3505 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.9035. Min Act: -0.1700
Data Index: 44374 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.8400. Min Act: -0.1700
Data Index: 6451373 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.8082. Min Act: -0.1700
Data Index: 7950102 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.8241. Min Act: -0.1700
Data Index: 6334072 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.8082. Min Act: -0.1700
Data Index: 4056425 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7922. Min Act: -0.1700
Data Index: 3398831 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.8082. Min Act: -0.1700
Data Index: 2441145 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7922. Min Act: -0.1700
Data Index: 5759026 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7922. Min Act: -0.1700
Data Index: 2088424 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7763. Min Act: -0.1700
Data Index: 4039607 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7763. Min Act: -0.1700
Data Index: 4923224 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7603. Min Act: -0.1700
Data Index: 2480155 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7444. Min Act: -0.1700
Data Index: 2480137 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7603. Min Act: -0.1700
Data Index: 4558724 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7444. Min Act: -0.1700
Data Index: 216502 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7444. Min Act: -0.1700
Data Index: 6866783 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7444. Min Act: -0.1700
Data Index: 4192937 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7284. Min Act: -0.1700
Data Index: 5696430 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7284. Min Act: -0.1700
Data Index: 1817335 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9035. Min Range: -2.9035
Max Act: 2.7284. Min Act: -0.1700
Data Index: 2480143 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19