Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5670 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.9729. Min Act: -0.1700
Data Index: 150577 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.8167. Min Act: -0.1700
Data Index: 2211216 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.7542. Min Act: -0.1700
Data Index: 6439110 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.7542. Min Act: -0.1700
Data Index: 3308471 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.6604. Min Act: -0.1700
Data Index: 7497245 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5979. Min Act: -0.1700
Data Index: 501262 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5979. Min Act: -0.1700
Data Index: 6714175 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5979. Min Act: -0.1700
Data Index: 656999 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5667. Min Act: -0.1700
Data Index: 6971793 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5354. Min Act: -0.1700
Data Index: 3789246 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5354. Min Act: -0.1700
Data Index: 3085734 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5042. Min Act: -0.1700
Data Index: 4668910 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.5042. Min Act: -0.1700
Data Index: 4081518 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.4729. Min Act: -0.1700
Data Index: 309892 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.4729. Min Act: -0.1700
Data Index: 8614935 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.4729. Min Act: -0.1700
Data Index: 8394548 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.4417. Min Act: -0.1700
Data Index: 3904472 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.4417. Min Act: -0.1700
Data Index: 794812 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.4417. Min Act: -0.1700
Data Index: 1684525 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9729. Min Range: -5.9729
Max Act: 5.4417. Min Act: -0.1700
Data Index: 2385576 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19