Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4673 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.3915. Min Act: -0.1700
Data Index: 4406580 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.3915. Min Act: -0.1700
Data Index: 1181658 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.2040. Min Act: -0.1700
Data Index: 6332053 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.2040. Min Act: -0.1700
Data Index: 6332456 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.1415. Min Act: -0.1700
Data Index: 6860936 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.1415. Min Act: -0.1700
Data Index: 5384382 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.1103. Min Act: -0.1700
Data Index: 7761491 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.0790. Min Act: -0.1700
Data Index: 2663905 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.0478. Min Act: -0.1700
Data Index: 8603194 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.0790. Min Act: -0.1700
Data Index: 12912 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.0165. Min Act: -0.1700
Data Index: 5591161 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.0165. Min Act: -0.1700
Data Index: 1559601 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.0478. Min Act: -0.1700
Data Index: 1643512 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3915. Min Range: -5.3915
Max Act: 5.0165. Min Act: -0.1700
Data Index: 1757850 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3915. Min Range: -5.3915
Max Act: 4.9540. Min Act: -0.1700
Data Index: 5893217 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3915. Min Range: -5.3915
Max Act: 4.9540. Min Act: -0.1700
Data Index: 7052083 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3915. Min Range: -5.3915
Max Act: 4.9540. Min Act: -0.1700
Data Index: 1643518 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3915. Min Range: -5.3915
Max Act: 4.9540. Min Act: -0.1700
Data Index: 3384343 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3915. Min Range: -5.3915
Max Act: 4.9853. Min Act: -0.1700
Data Index: 3071259 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3915. Min Range: -5.3915
Max Act: 4.9228. Min Act: -0.1700
Data Index: 5689013 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19