Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1337 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.4095. Min Act: -0.1700
Data Index: 6124040 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.3157. Min Act: -0.1700
Data Index: 7120953 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.2532. Min Act: -0.1700
Data Index: 500775 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.1907. Min Act: -0.1700
Data Index: 7373603 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.1282. Min Act: -0.1700
Data Index: 8173049 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.1595. Min Act: -0.1700
Data Index: 6768932 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.1282. Min Act: -0.1700
Data Index: 869777 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.1595. Min Act: -0.1700
Data Index: 3258586 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.1282. Min Act: -0.1700
Data Index: 1518949 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.1282. Min Act: -0.1700
Data Index: 7240800 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0970. Min Act: -0.1700
Data Index: 6095345 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0970. Min Act: -0.1700
Data Index: 823223 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0970. Min Act: -0.1700
Data Index: 979876 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0657. Min Act: -0.1700
Data Index: 5052608 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0657. Min Act: -0.1700
Data Index: 6501929 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0657. Min Act: -0.1700
Data Index: 2516159 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0657. Min Act: -0.1700
Data Index: 3824207 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0345. Min Act: -0.1700
Data Index: 2295229 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0345. Min Act: -0.1700
Data Index: 3905414 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4095. Min Range: -5.4095
Max Act: 5.0345. Min Act: -0.1700
Data Index: 7317362 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19