Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 55 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.9315. Min Act: -0.1700
Data Index: 4590319 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.9002. Min Act: -0.1700
Data Index: 3345380 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.8065. Min Act: -0.1700
Data Index: 3660170 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.8065. Min Act: -0.1700
Data Index: 6909005 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7752. Min Act: -0.1700
Data Index: 1624527 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7752. Min Act: -0.1700
Data Index: 6506141 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7127. Min Act: -0.1700
Data Index: 3782756 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2407479 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2889716 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7127. Min Act: -0.1700
Data Index: 1573478 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7127. Min Act: -0.1700
Data Index: 2385378 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7127. Min Act: -0.1700
Data Index: 4219332 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.7127. Min Act: -0.1700
Data Index: 7083963 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.6815. Min Act: -0.1700
Data Index: 7582520 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.6815. Min Act: -0.1700
Data Index: 1882082 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.6815. Min Act: -0.1700
Data Index: 6914638 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.6815. Min Act: -0.1700
Data Index: 8244636 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.6815. Min Act: -0.1700
Data Index: 237360 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.6815. Min Act: -0.1700
Data Index: 5973804 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9315. Min Range: -5.9315
Max Act: 5.6502. Min Act: -0.1700
Data Index: 2869766 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19