Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4856 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.9908. Min Act: -0.1700
Data Index: 4300961 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.9595. Min Act: -0.1700
Data Index: 7677520 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.8345. Min Act: -0.1700
Data Index: 2889958 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.7720. Min Act: -0.1700
Data Index: 2253220 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.7408. Min Act: -0.1700
Data Index: 2172703 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.7408. Min Act: -0.1700
Data Index: 5249026 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.7408. Min Act: -0.1700
Data Index: 3495200 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.7095. Min Act: -0.1700
Data Index: 3388729 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6783. Min Act: -0.1700
Data Index: 263713 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6783. Min Act: -0.1700
Data Index: 2437117 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6470. Min Act: -0.1700
Data Index: 32011 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6470. Min Act: -0.1700
Data Index: 4636723 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6470. Min Act: -0.1700
Data Index: 3789894 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6158. Min Act: -0.1700
Data Index: 4204733 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6158. Min Act: -0.1700
Data Index: 2369340 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6158. Min Act: -0.1700
Data Index: 1290060 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6158. Min Act: -0.1700
Data Index: 3396363 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6158. Min Act: -0.1700
Data Index: 1554453 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6158. Min Act: -0.1700
Data Index: 869378 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9908. Min Range: -5.9908
Max Act: 5.6158. Min Act: -0.1700
Data Index: 3238049 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19