Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1886 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.1295. Min Act: -0.1700
Data Index: 3433213 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0982. Min Act: -0.1700
Data Index: 4048549 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0670. Min Act: -0.1700
Data Index: 5776613 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1295. Min Range: -5.1295
Max Act: 5.0045. Min Act: -0.1700
Data Index: 3332588 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9732. Min Act: -0.1700
Data Index: 3440336 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9420. Min Act: -0.1700
Data Index: 2793793 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9420. Min Act: -0.1700
Data Index: 5836619 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9420. Min Act: -0.1700
Data Index: 152339 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9107. Min Act: -0.1700
Data Index: 1553912 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9107. Min Act: -0.1700
Data Index: 2918283 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9107. Min Act: -0.1700
Data Index: 4533461 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9420. Min Act: -0.1700
Data Index: 8479202 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9107. Min Act: -0.1700
Data Index: 467352 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8795. Min Act: -0.1700
Data Index: 8146876 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8795. Min Act: -0.1700
Data Index: 888671 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.9107. Min Act: -0.1700
Data Index: 1586064 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8482. Min Act: -0.1700
Data Index: 5362761 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8482. Min Act: -0.1700
Data Index: 6573599 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8482. Min Act: -0.1700
Data Index: 8702624 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1295. Min Range: -5.1295
Max Act: 4.8482. Min Act: -0.1700
Data Index: 2161713 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19