Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4503 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.9865. Min Act: -0.1700
Data Index: 5167997 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.7365. Min Act: -0.1700
Data Index: 5099678 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.7053. Min Act: -0.1700
Data Index: 2409076 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.6115. Min Act: -0.1700
Data Index: 6103400 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.5490. Min Act: -0.1700
Data Index: 234154 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.5178. Min Act: -0.1700
Data Index: 800705 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.4865. Min Act: -0.1700
Data Index: 7912493 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.4865. Min Act: -0.1700
Data Index: 5508691 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.4553. Min Act: -0.1700
Data Index: 239341 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.4553. Min Act: -0.1700
Data Index: 4784157 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.4240. Min Act: -0.1700
Data Index: 7038083 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.4240. Min Act: -0.1700
Data Index: 5389883 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3928. Min Act: -0.1700
Data Index: 2569251 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3615. Min Act: -0.1700
Data Index: 6294192 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3615. Min Act: -0.1700
Data Index: 3368269 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3928. Min Act: -0.1700
Data Index: 2049161 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3928. Min Act: -0.1700
Data Index: 1398843 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3928. Min Act: -0.1700
Data Index: 7115927 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3615. Min Act: -0.1700
Data Index: 5854700 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9865. Min Range: -5.9865
Max Act: 5.3615. Min Act: -0.1700
Data Index: 2737421 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19