Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0093. Min Range: -7.0093
Max Act: 7.0093. Min Act: -0.1700
Data Index: 2986050 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.9781. Min Act: -0.1700
Data Index: 2077315 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.9468. Min Act: -0.1700
Data Index: 5961254 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.8843. Min Act: -0.1700
Data Index: 1874792 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.8531. Min Act: -0.1700
Data Index: 2938780 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.8531. Min Act: -0.1700
Data Index: 3243320 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.7906. Min Act: -0.1700
Data Index: 3691163 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.7593. Min Act: -0.1700
Data Index: 2855303 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.7906. Min Act: -0.1700
Data Index: 883185 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.7593. Min Act: -0.1700
Data Index: 504913 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.7593. Min Act: -0.1700
Data Index: 3033647 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.7593. Min Act: -0.1700
Data Index: 4089231 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.6968. Min Act: -0.1700
Data Index: 1810648 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.7593. Min Act: -0.1700
Data Index: 5318060 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.6968. Min Act: -0.1700
Data Index: 3414857 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.6968. Min Act: -0.1700
Data Index: 6246162 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.6968. Min Act: -0.1700
Data Index: 5226863 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.6656. Min Act: -0.1700
Data Index: 2140003 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.6343. Min Act: -0.1700
Data Index: 2663930 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0093. Min Range: -7.0093
Max Act: 6.6343. Min Act: -0.1700
Data Index: 7725910 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19