Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5212 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4269. Min Range: -4.4269
Max Act: 4.4269. Min Act: -0.1700
Data Index: 3447629 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4269. Min Range: -4.4269
Max Act: 4.1143. Min Act: -0.1700
Data Index: 7830672 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4269. Min Range: -4.4269
Max Act: 4.0518. Min Act: -0.1700
Data Index: 1569970 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4269. Min Range: -4.4269
Max Act: 4.0206. Min Act: -0.1700
Data Index: 4885314 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4269. Min Range: -4.4269
Max Act: 4.0206. Min Act: -0.1700
Data Index: 2341664 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.9893. Min Act: -0.1700
Data Index: 4885309 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.9893. Min Act: -0.1700
Data Index: 4076849 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.9580. Min Act: -0.1700
Data Index: 1037539 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.9580. Min Act: -0.1700
Data Index: 6281777 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.9268. Min Act: -0.1700
Data Index: 3602217 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8643. Min Act: -0.1700
Data Index: 7903485 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8955. Min Act: -0.1700
Data Index: 4464379 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8955. Min Act: -0.1700
Data Index: 4615343 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8955. Min Act: -0.1700
Data Index: 1398051 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8643. Min Act: -0.1700
Data Index: 4730308 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8643. Min Act: -0.1700
Data Index: 7155031 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8643. Min Act: -0.1700
Data Index: 1325862 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8955. Min Act: -0.1700
Data Index: 5790360 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8955. Min Act: -0.1700
Data Index: 8033019 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4269. Min Range: -4.4269
Max Act: 3.8643. Min Act: -0.1700
Data Index: 4885313 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19