Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 263 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0450. Min Range: -4.0450
Max Act: 4.0450. Min Act: -0.1700
Data Index: 1453260 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7949. Min Act: -0.1700
Data Index: 8525007 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7636. Min Act: -0.1700
Data Index: 6222562 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7636. Min Act: -0.1700
Data Index: 3151883 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7323. Min Act: -0.1700
Data Index: 7732523 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7323. Min Act: -0.1700
Data Index: 6683196 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7636. Min Act: -0.1700
Data Index: 5346041 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7323. Min Act: -0.1700
Data Index: 195701 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7323. Min Act: -0.1700
Data Index: 331311 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7323. Min Act: -0.1700
Data Index: 7184335 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7011. Min Act: -0.1700
Data Index: 2669738 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7011. Min Act: -0.1700
Data Index: 8428268 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.6854. Min Act: -0.1700
Data Index: 4218989 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.6698. Min Act: -0.1700
Data Index: 5238008 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.6854. Min Act: -0.1700
Data Index: 4849504 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.7011. Min Act: -0.1700
Data Index: 2720225 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.6698. Min Act: -0.1700
Data Index: 2465703 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.6541. Min Act: -0.1700
Data Index: 7966164 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.6385. Min Act: -0.1700
Data Index: 1869123 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0450. Min Range: -4.0450
Max Act: 3.6228. Min Act: -0.1700
Data Index: 771624 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19