Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4514 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2843. Min Range: -6.2843
Max Act: 6.2843. Min Act: -0.1700
Data Index: 1016331 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2843. Min Range: -6.2843
Max Act: 6.1906. Min Act: -0.1700
Data Index: 1016332 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2843. Min Range: -6.2843
Max Act: 6.0656. Min Act: -0.1700
Data Index: 5562122 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.9406. Min Act: -0.1700
Data Index: 1644759 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8781. Min Act: -0.1700
Data Index: 7672816 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8781. Min Act: -0.1700
Data Index: 2969528 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8781. Min Act: -0.1700
Data Index: 6698106 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8781. Min Act: -0.1700
Data Index: 8688428 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8781. Min Act: -0.1700
Data Index: 387787 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8468. Min Act: -0.1700
Data Index: 7396159 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8468. Min Act: -0.1700
Data Index: 4396650 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.8156. Min Act: -0.1700
Data Index: 2598976 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7843. Min Act: -0.1700
Data Index: 1897543 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7843. Min Act: -0.1700
Data Index: 2471400 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7843. Min Act: -0.1700
Data Index: 2609320 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7843. Min Act: -0.1700
Data Index: 726138 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7843. Min Act: -0.1700
Data Index: 6410153 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7531. Min Act: -0.1700
Data Index: 5981152 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7531. Min Act: -0.1700
Data Index: 2553330 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2843. Min Range: -6.2843
Max Act: 5.7218. Min Act: -0.1700
Data Index: 1316057 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19