Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.6375. Min Act: -0.1700
Data Index: 3250290 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.3875. Min Act: -0.1700
Data Index: 6811247 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.3562. Min Act: -0.1700
Data Index: 2215668 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.3562. Min Act: -0.1700
Data Index: 3804008 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.3562. Min Act: -0.1700
Data Index: 6341292 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.3250. Min Act: -0.1700
Data Index: 1609128 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2937. Min Act: -0.1700
Data Index: 6173789 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2937. Min Act: -0.1700
Data Index: 8700324 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2937. Min Act: -0.1700
Data Index: 2636816 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2625. Min Act: -0.1700
Data Index: 1732324 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2625. Min Act: -0.1700
Data Index: 6978909 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2937. Min Act: -0.1700
Data Index: 4140177 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2625. Min Act: -0.1700
Data Index: 3483358 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2625. Min Act: -0.1700
Data Index: 2890430 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2625. Min Act: -0.1700
Data Index: 879179 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2312. Min Act: -0.1700
Data Index: 2831472 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2312. Min Act: -0.1700
Data Index: 2754835 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2312. Min Act: -0.1700
Data Index: 3954621 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2312. Min Act: -0.1700
Data Index: 2012115 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6375. Min Range: -4.6375
Max Act: 4.2312. Min Act: -0.1700
Data Index: 5972560 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19