Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2112 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.9181. Min Act: -0.1700
Data Index: 7833918 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.8244. Min Act: -0.1700
Data Index: 2405105 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.7306. Min Act: -0.1700
Data Index: 8101706 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.7306. Min Act: -0.1700
Data Index: 114724 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.7306. Min Act: -0.1700
Data Index: 8231910 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.6994. Min Act: -0.1700
Data Index: 4855464 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.7306. Min Act: -0.1700
Data Index: 7722363 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.6994. Min Act: -0.1700
Data Index: 2575369 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.6369. Min Act: -0.1700
Data Index: 3225256 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.6369. Min Act: -0.1700
Data Index: 5659477 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.5744. Min Act: -0.1700
Data Index: 4188865 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.5744. Min Act: -0.1700
Data Index: 1877209 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.5431. Min Act: -0.1700
Data Index: 2050095 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.5431. Min Act: -0.1700
Data Index: 5291269 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.5119. Min Act: -0.1700
Data Index: 6633247 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4806. Min Act: -0.1700
Data Index: 1798649 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4806. Min Act: -0.1700
Data Index: 1303680 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4806. Min Act: -0.1700
Data Index: 386454 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4806. Min Act: -0.1700
Data Index: 3178920 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9181. Min Range: -5.9181
Max Act: 5.4806. Min Act: -0.1700
Data Index: 4317529 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19