Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4171 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.6562. Min Act: -0.1700
Data Index: 7876145 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.6249. Min Act: -0.1700
Data Index: 1893554 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.6249. Min Act: -0.1700
Data Index: 7651068 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.6249. Min Act: -0.1700
Data Index: 4994939 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.5937. Min Act: -0.1700
Data Index: 3998747 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.5937. Min Act: -0.1700
Data Index: 7131727 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.5624. Min Act: -0.1700
Data Index: 4082714 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.5312. Min Act: -0.1700
Data Index: 6418289 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.5312. Min Act: -0.1700
Data Index: 3236667 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.5624. Min Act: -0.1700
Data Index: 1140280 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4999. Min Act: -0.1700
Data Index: 7847521 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4999. Min Act: -0.1700
Data Index: 8194334 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4999. Min Act: -0.1700
Data Index: 1245864 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4999. Min Act: -0.1700
Data Index: 518248 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4687. Min Act: -0.1700
Data Index: 5014573 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4374. Min Act: -0.1700
Data Index: 2206582 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4687. Min Act: -0.1700
Data Index: 2394492 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4687. Min Act: -0.1700
Data Index: 2165942 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4687. Min Act: -0.1700
Data Index: 2040644 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6562. Min Range: -5.6562
Max Act: 5.4374. Min Act: -0.1700
Data Index: 2908275 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19