Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.2885. Min Act: -0.1700
Data Index: 8470698 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.1323. Min Act: -0.1700
Data Index: 5548168 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.1010. Min Act: -0.1700
Data Index: 2485791 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.1010. Min Act: -0.1700
Data Index: 8714630 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.0073. Min Act: -0.1700
Data Index: 5108226 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.0073. Min Act: -0.1700
Data Index: 1018339 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.0073. Min Act: -0.1700
Data Index: 4528392 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.0073. Min Act: -0.1700
Data Index: 5929685 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9760. Min Act: -0.1700
Data Index: 3695331 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9760. Min Act: -0.1700
Data Index: 763122 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9760. Min Act: -0.1700
Data Index: 4496996 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2885. Min Range: -5.2885
Max Act: 5.0073. Min Act: -0.1700
Data Index: 7694583 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9760. Min Act: -0.1700
Data Index: 7829949 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9135. Min Act: -0.1700
Data Index: 8269040 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9448. Min Act: -0.1700
Data Index: 7128526 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9448. Min Act: -0.1700
Data Index: 3769901 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9448. Min Act: -0.1700
Data Index: 2319203 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9135. Min Act: -0.1700
Data Index: 4388475 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9135. Min Act: -0.1700
Data Index: 750105 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2885. Min Range: -5.2885
Max Act: 4.9135. Min Act: -0.1700
Data Index: 4885693 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19