Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5038 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.3175. Min Act: -0.1700
Data Index: 3946383 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2863. Min Act: -0.1700
Data Index: 98565 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2863. Min Act: -0.1700
Data Index: 3219737 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2863. Min Act: -0.1700
Data Index: 733866 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2550. Min Act: -0.1700
Data Index: 3946382 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2550. Min Act: -0.1700
Data Index: 8123888 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2550. Min Act: -0.1700
Data Index: 8715951 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2238. Min Act: -0.1700
Data Index: 3183513 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2238. Min Act: -0.1700
Data Index: 4714458 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2238. Min Act: -0.1700
Data Index: 647391 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2238. Min Act: -0.1700
Data Index: 1830887 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.2238. Min Act: -0.1700
Data Index: 1034369 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 4872955 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 5167324 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 2467622 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 1434826 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 3250169 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 388388 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 1462338 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3175. Min Range: -5.3175
Max Act: 5.1925. Min Act: -0.1700
Data Index: 4503691 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19