Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2346 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.2835. Min Act: -0.1700
Data Index: 7050336 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.1897. Min Act: -0.1700
Data Index: 1038926 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.1272. Min Act: -0.1700
Data Index: 6268568 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.0960. Min Act: -0.1700
Data Index: 4563585 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.0335. Min Act: -0.1700
Data Index: 7929666 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.0647. Min Act: -0.1700
Data Index: 1913640 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.0335. Min Act: -0.1700
Data Index: 8696430 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.9710. Min Act: -0.1700
Data Index: 5120842 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.0022. Min Act: -0.1700
Data Index: 3437635 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2835. Min Range: -6.2835
Max Act: 6.0022. Min Act: -0.1700
Data Index: 275904 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.9710. Min Act: -0.1700
Data Index: 539490 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.9397. Min Act: -0.1700
Data Index: 664744 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.9085. Min Act: -0.1700
Data Index: 7654973 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.8460. Min Act: -0.1700
Data Index: 1382415 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.8460. Min Act: -0.1700
Data Index: 6723442 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.8460. Min Act: -0.1700
Data Index: 114570 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.7835. Min Act: -0.1700
Data Index: 8372407 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5482678 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.8147. Min Act: -0.1700
Data Index: 6429129 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2835. Min Range: -6.2835
Max Act: 5.7522. Min Act: -0.1700
Data Index: 2839269 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19