Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.8109. Min Act: -0.1700
Data Index: 5791954 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7953. Min Act: -0.1700
Data Index: 4124540 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7484. Min Act: -0.1700
Data Index: 6944609 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7640. Min Act: -0.1700
Data Index: 7154139 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7171. Min Act: -0.1700
Data Index: 7840548 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.7171. Min Act: -0.1700
Data Index: 3441436 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6858. Min Act: -0.1700
Data Index: 5375669 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6858. Min Act: -0.1700
Data Index: 5893988 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6858. Min Act: -0.1700
Data Index: 972533 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6858. Min Act: -0.1700
Data Index: 1066300 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6701. Min Act: -0.1700
Data Index: 5913276 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6701. Min Act: -0.1700
Data Index: 8026140 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6545. Min Act: -0.1700
Data Index: 3133240 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6545. Min Act: -0.1700
Data Index: 7311957 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6388. Min Act: -0.1700
Data Index: 3072203 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6388. Min Act: -0.1700
Data Index: 3134860 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6545. Min Act: -0.1700
Data Index: 2035149 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6388. Min Act: -0.1700
Data Index: 3320049 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6545. Min Act: -0.1700
Data Index: 2474601 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8109. Min Range: -3.8109
Max Act: 3.6545. Min Act: -0.1700
Data Index: 2771492 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19