Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2249. Min Range: -6.2249
Max Act: 6.2249. Min Act: -0.1700
Data Index: 4720970 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2249. Min Range: -6.2249
Max Act: 6.1937. Min Act: -0.1700
Data Index: 1984144 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2249. Min Range: -6.2249
Max Act: 6.0062. Min Act: -0.1700
Data Index: 8353950 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.9437. Min Act: -0.1700
Data Index: 3738435 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.9124. Min Act: -0.1700
Data Index: 4952000 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.8812. Min Act: -0.1700
Data Index: 5204603 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.8812. Min Act: -0.1700
Data Index: 4444226 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.8187. Min Act: -0.1700
Data Index: 3918431 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.8187. Min Act: -0.1700
Data Index: 371409 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7874. Min Act: -0.1700
Data Index: 2700564 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7874. Min Act: -0.1700
Data Index: 926786 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7562. Min Act: -0.1700
Data Index: 3601310 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7874. Min Act: -0.1700
Data Index: 6072738 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7562. Min Act: -0.1700
Data Index: 5559142 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7562. Min Act: -0.1700
Data Index: 6861662 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7249. Min Act: -0.1700
Data Index: 7782011 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.7249. Min Act: -0.1700
Data Index: 6515197 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.6937. Min Act: -0.1700
Data Index: 7059210 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.6937. Min Act: -0.1700
Data Index: 3079385 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2249. Min Range: -6.2249
Max Act: 5.6312. Min Act: -0.1700
Data Index: 2823621 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19