Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2814 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2146. Min Range: -7.2146
Max Act: 7.2146. Min Act: -0.1700
Data Index: 3249541 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.9021. Min Act: -0.1700
Data Index: 3105815 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.8708. Min Act: -0.1700
Data Index: 2047920 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.9021. Min Act: -0.1700
Data Index: 5804891 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.7771. Min Act: -0.1700
Data Index: 1340723 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.7146. Min Act: -0.1700
Data Index: 8575195 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.7146. Min Act: -0.1700
Data Index: 1298112 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.6833. Min Act: -0.1700
Data Index: 7760076 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.6208. Min Act: -0.1700
Data Index: 7360629 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5896. Min Act: -0.1700
Data Index: 4354401 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5896. Min Act: -0.1700
Data Index: 3304128 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5896. Min Act: -0.1700
Data Index: 3969073 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5583. Min Act: -0.1700
Data Index: 7381465 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5271. Min Act: -0.1700
Data Index: 906376 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5271. Min Act: -0.1700
Data Index: 3490298 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5271. Min Act: -0.1700
Data Index: 2125425 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.5271. Min Act: -0.1700
Data Index: 3445577 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.4958. Min Act: -0.1700
Data Index: 1422201 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.4958. Min Act: -0.1700
Data Index: 4852346 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2146. Min Range: -7.2146
Max Act: 6.4646. Min Act: -0.1700
Data Index: 5339278 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19