Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3023 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.5756. Min Act: -0.1700
Data Index: 8595898 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.5131. Min Act: -0.1700
Data Index: 4993092 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.3256. Min Act: -0.1700
Data Index: 1110287 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.2943. Min Act: -0.1700
Data Index: 30738 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.2943. Min Act: -0.1700
Data Index: 6744902 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.2631. Min Act: -0.1700
Data Index: 6413745 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.2318. Min Act: -0.1700
Data Index: 5972359 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.1068. Min Act: -0.1700
Data Index: 3927979 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.1068. Min Act: -0.1700
Data Index: 1145411 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.1068. Min Act: -0.1700
Data Index: 6943638 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.1068. Min Act: -0.1700
Data Index: 5433152 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.1068. Min Act: -0.1700
Data Index: 3622754 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.0756. Min Act: -0.1700
Data Index: 5555371 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.0756. Min Act: -0.1700
Data Index: 5571328 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.0131. Min Act: -0.1700
Data Index: 232704 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.0443. Min Act: -0.1700
Data Index: 4817118 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.0131. Min Act: -0.1700
Data Index: 4863522 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.0131. Min Act: -0.1700
Data Index: 4757743 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5756. Min Range: -6.5756
Max Act: 6.0131. Min Act: -0.1700
Data Index: 2366654 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5756. Min Range: -6.5756
Max Act: 5.9818. Min Act: -0.1700
Data Index: 7772674 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19