Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3127 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.6364. Min Act: -0.1700
Data Index: 7534129 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.5739. Min Act: -0.1700
Data Index: 7133487 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.5427. Min Act: -0.1700
Data Index: 4592238 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.4802. Min Act: -0.1700
Data Index: 5655481 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.3552. Min Act: -0.1700
Data Index: 5818841 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.2302. Min Act: -0.1700
Data Index: 969894 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.1677. Min Act: -0.1700
Data Index: 969900 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.1989. Min Act: -0.1700
Data Index: 8541345 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.1364. Min Act: -0.1700
Data Index: 4446136 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.1052. Min Act: -0.1700
Data Index: 4747637 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.0739. Min Act: -0.1700
Data Index: 6163537 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.0739. Min Act: -0.1700
Data Index: 8680563 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 8114526 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.0427. Min Act: -0.1700
Data Index: 797181 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.0427. Min Act: -0.1700
Data Index: 421135 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 8230212 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6364. Min Range: -5.6364
Max Act: 5.0114. Min Act: -0.1700
Data Index: 3660935 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6364. Min Range: -5.6364
Max Act: 4.9802. Min Act: -0.1700
Data Index: 8145594 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6364. Min Range: -5.6364
Max Act: 4.9489. Min Act: -0.1700
Data Index: 1232816 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6364. Min Range: -5.6364
Max Act: 4.9489. Min Act: -0.1700
Data Index: 2865303 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19