Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.9442. Min Act: -0.1700
Data Index: 7691460 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.8817. Min Act: -0.1700
Data Index: 8752356 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.8192. Min Act: -0.1700
Data Index: 6302007 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.6629. Min Act: -0.1700
Data Index: 8474092 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.4129. Min Act: -0.1700
Data Index: 1421608 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.3817. Min Act: -0.1700
Data Index: 6729273 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.3817. Min Act: -0.1700
Data Index: 2054899 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.4129. Min Act: -0.1700
Data Index: 6973142 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.3817. Min Act: -0.1700
Data Index: 2776566 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.3817. Min Act: -0.1700
Data Index: 5899797 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.3504. Min Act: -0.1700
Data Index: 2084713 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.3192. Min Act: -0.1700
Data Index: 4303580 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.2879. Min Act: -0.1700
Data Index: 2740832 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.2567. Min Act: -0.1700
Data Index: 8555932 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.2567. Min Act: -0.1700
Data Index: 1516593 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.2254. Min Act: -0.1700
Data Index: 1172627 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.2254. Min Act: -0.1700
Data Index: 1093378 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.1942. Min Act: -0.1700
Data Index: 688244 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.2254. Min Act: -0.1700
Data Index: 2068069 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9442. Min Range: -7.9442
Max Act: 7.1942. Min Act: -0.1700
Data Index: 5667128 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19