Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 664 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2932. Min Range: -6.2932
Max Act: 6.2932. Min Act: -0.1700
Data Index: 286869 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.9182. Min Act: -0.1700
Data Index: 5200541 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.8870. Min Act: -0.1700
Data Index: 255367 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.6057. Min Act: -0.1700
Data Index: 1445817 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.5745. Min Act: -0.1700
Data Index: 8231447 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.6057. Min Act: -0.1700
Data Index: 6785489 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.5120. Min Act: -0.1700
Data Index: 7971316 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.5120. Min Act: -0.1700
Data Index: 1724023 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.5120. Min Act: -0.1700
Data Index: 8173765 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.4807. Min Act: -0.1700
Data Index: 4171282 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.4807. Min Act: -0.1700
Data Index: 5488286 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.4495. Min Act: -0.1700
Data Index: 2835654 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.3870. Min Act: -0.1700
Data Index: 3212363 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.4182. Min Act: -0.1700
Data Index: 6356218 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.4182. Min Act: -0.1700
Data Index: 662850 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.4182. Min Act: -0.1700
Data Index: 5419166 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.3870. Min Act: -0.1700
Data Index: 6471118 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.3870. Min Act: -0.1700
Data Index: 7176786 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.3557. Min Act: -0.1700
Data Index: 4850411 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2932. Min Range: -6.2932
Max Act: 5.3870. Min Act: -0.1700
Data Index: 4037130 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19