Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.7271. Min Act: -0.1700
Data Index: 6379746 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.5396. Min Act: -0.1700
Data Index: 822200 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.5083. Min Act: -0.1700
Data Index: 7042706 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.5083. Min Act: -0.1700
Data Index: 5888239 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.4146. Min Act: -0.1700
Data Index: 4739789 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.3833. Min Act: -0.1700
Data Index: 6156954 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.3833. Min Act: -0.1700
Data Index: 2642048 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.3833. Min Act: -0.1700
Data Index: 5027919 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.3208. Min Act: -0.1700
Data Index: 7512275 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.3208. Min Act: -0.1700
Data Index: 5276178 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2896. Min Act: -0.1700
Data Index: 8682332 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2583. Min Act: -0.1700
Data Index: 8106106 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2583. Min Act: -0.1700
Data Index: 4801587 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2583. Min Act: -0.1700
Data Index: 5774032 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2271. Min Act: -0.1700
Data Index: 2657516 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2271. Min Act: -0.1700
Data Index: 7975201 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2583. Min Act: -0.1700
Data Index: 2212454 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2271. Min Act: -0.1700
Data Index: 5262981 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2271. Min Act: -0.1700
Data Index: 4801589 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7271. Min Range: -4.7271
Max Act: 4.2583. Min Act: -0.1700
Data Index: 6483752 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19