Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3434 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.5741. Min Act: -0.1700
Data Index: 3053229 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.4491. Min Act: -0.1700
Data Index: 2066085 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.3241. Min Act: -0.1700
Data Index: 5123404 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.2616. Min Act: -0.1700
Data Index: 6659650 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.2616. Min Act: -0.1700
Data Index: 4457157 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.2616. Min Act: -0.1700
Data Index: 6830456 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.1366. Min Act: -0.1700
Data Index: 7288829 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.1991. Min Act: -0.1700
Data Index: 7988302 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.1991. Min Act: -0.1700
Data Index: 6824145 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.1054. Min Act: -0.1700
Data Index: 6038982 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5741. Min Range: -8.5741
Max Act: 8.0741. Min Act: -0.1700
Data Index: 7019733 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9491. Min Act: -0.1700
Data Index: 1633359 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9491. Min Act: -0.1700
Data Index: 8656171 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9491. Min Act: -0.1700
Data Index: 3022159 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9491. Min Act: -0.1700
Data Index: 6057042 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9179. Min Act: -0.1700
Data Index: 2163113 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9179. Min Act: -0.1700
Data Index: 4705447 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9179. Min Act: -0.1700
Data Index: 4024354 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.9179. Min Act: -0.1700
Data Index: 6266302 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5741. Min Range: -8.5741
Max Act: 7.8866. Min Act: -0.1700
Data Index: 6901383 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19