Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.6130. Min Act: -0.1700
Data Index: 3836111 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.5817. Min Act: -0.1700
Data Index: 5907150 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8726264 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3942. Min Act: -0.1700
Data Index: 4764604 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3630. Min Act: -0.1700
Data Index: 3421571 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3630. Min Act: -0.1700
Data Index: 229735 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3317. Min Act: -0.1700
Data Index: 714568 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3317. Min Act: -0.1700
Data Index: 8477323 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3005. Min Act: -0.1700
Data Index: 5826941 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3005. Min Act: -0.1700
Data Index: 8317093 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3005. Min Act: -0.1700
Data Index: 8317087 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3005. Min Act: -0.1700
Data Index: 988121 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.3005. Min Act: -0.1700
Data Index: 6227538 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.2692. Min Act: -0.1700
Data Index: 1083147 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.2692. Min Act: -0.1700
Data Index: 3172872 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.2692. Min Act: -0.1700
Data Index: 8385370 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.2380. Min Act: -0.1700
Data Index: 6637667 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.2692. Min Act: -0.1700
Data Index: 7080237 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.2380. Min Act: -0.1700
Data Index: 1635184 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6130. Min Range: -6.6130
Max Act: 6.2067. Min Act: -0.1700
Data Index: 971807 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19