Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.2373. Min Act: -0.1700
Data Index: 4682583 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.2060. Min Act: -0.1700
Data Index: 3792931 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.2060. Min Act: -0.1700
Data Index: 2577227 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2373. Min Range: -6.2373
Max Act: 6.1435. Min Act: -0.1700
Data Index: 3459310 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9873. Min Act: -0.1700
Data Index: 2807930 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9560. Min Act: -0.1700
Data Index: 6826718 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9248. Min Act: -0.1700
Data Index: 5882509 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9248. Min Act: -0.1700
Data Index: 7711573 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.9248. Min Act: -0.1700
Data Index: 4990381 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8623. Min Act: -0.1700
Data Index: 4746258 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8623. Min Act: -0.1700
Data Index: 3894186 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8623. Min Act: -0.1700
Data Index: 7948580 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.7998. Min Act: -0.1700
Data Index: 4488501 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8310. Min Act: -0.1700
Data Index: 6550385 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.7998. Min Act: -0.1700
Data Index: 2637827 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.7998. Min Act: -0.1700
Data Index: 4939244 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.8310. Min Act: -0.1700
Data Index: 4708343 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.7998. Min Act: -0.1700
Data Index: 4148151 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.7373. Min Act: -0.1700
Data Index: 514376 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2373. Min Range: -6.2373
Max Act: 5.7685. Min Act: -0.1700
Data Index: 1336000 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19