Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2753 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.9143. Min Act: -0.1700
Data Index: 540603 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.8205. Min Act: -0.1700
Data Index: 4310720 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.7580. Min Act: -0.1700
Data Index: 1085110 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.7580. Min Act: -0.1700
Data Index: 7301385 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.7580. Min Act: -0.1700
Data Index: 3076412 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.7268. Min Act: -0.1700
Data Index: 2435150 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6955. Min Act: -0.1700
Data Index: 4531262 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.7268. Min Act: -0.1700
Data Index: 2985003 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.7268. Min Act: -0.1700
Data Index: 2441376 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6955. Min Act: -0.1700
Data Index: 766147 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6643. Min Act: -0.1700
Data Index: 439997 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6643. Min Act: -0.1700
Data Index: 7981787 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6643. Min Act: -0.1700
Data Index: 8316024 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6330. Min Act: -0.1700
Data Index: 6883325 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6643. Min Act: -0.1700
Data Index: 4957173 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6330. Min Act: -0.1700
Data Index: 4585946 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6018. Min Act: -0.1700
Data Index: 6806716 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6018. Min Act: -0.1700
Data Index: 4635712 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.6018. Min Act: -0.1700
Data Index: 1549659 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9143. Min Range: -4.9143
Max Act: 4.5705. Min Act: -0.1700
Data Index: 5477029 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19