Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5487 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9819. Min Act: -0.1700
Data Index: 272116 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9506. Min Act: -0.1700
Data Index: 6179361 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9819. Min Act: -0.1700
Data Index: 6497156 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 5887381 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 70501 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7631. Min Act: -0.1700
Data Index: 7687586 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7006. Min Act: -0.1700
Data Index: 3711259 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7319. Min Act: -0.1700
Data Index: 8044847 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7319. Min Act: -0.1700
Data Index: 7346724 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7006. Min Act: -0.1700
Data Index: 4719215 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7006. Min Act: -0.1700
Data Index: 70141 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7006. Min Act: -0.1700
Data Index: 5439950 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.7006. Min Act: -0.1700
Data Index: 2005543 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.6694. Min Act: -0.1700
Data Index: 4566113 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.6694. Min Act: -0.1700
Data Index: 3421514 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.6694. Min Act: -0.1700
Data Index: 3312819 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.6694. Min Act: -0.1700
Data Index: 6531168 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.6381. Min Act: -0.1700
Data Index: 7161779 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.6381. Min Act: -0.1700
Data Index: 6881037 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.6381. Min Act: -0.1700
Data Index: 6502776 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19