Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4226. Min Range: -7.4226
Max Act: 7.4226. Min Act: -0.1700
Data Index: 3850529 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.9539. Min Act: -0.1700
Data Index: 2183440 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.9226. Min Act: -0.1700
Data Index: 3173181 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.8289. Min Act: -0.1700
Data Index: 1803831 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.7664. Min Act: -0.1700
Data Index: 561452 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.7664. Min Act: -0.1700
Data Index: 1201259 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.5789. Min Act: -0.1700
Data Index: 4603726 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.6101. Min Act: -0.1700
Data Index: 5134828 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.6101. Min Act: -0.1700
Data Index: 4024624 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.5789. Min Act: -0.1700
Data Index: 3437690 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.5476. Min Act: -0.1700
Data Index: 3714419 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.5476. Min Act: -0.1700
Data Index: 7386261 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.4851. Min Act: -0.1700
Data Index: 3048506 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.4851. Min Act: -0.1700
Data Index: 609907 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.4539. Min Act: -0.1700
Data Index: 2940048 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.4226. Min Act: -0.1700
Data Index: 3054265 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.3914. Min Act: -0.1700
Data Index: 6873838 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.3601. Min Act: -0.1700
Data Index: 3081864 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.4226. Min Act: -0.1700
Data Index: 3235116 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4226. Min Range: -7.4226
Max Act: 6.3914. Min Act: -0.1700
Data Index: 336845 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19