Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.9637. Min Act: -0.1700
Data Index: 5689189 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.7762. Min Act: -0.1700
Data Index: 6968738 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.7762. Min Act: -0.1700
Data Index: 7501761 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.7449. Min Act: -0.1700
Data Index: 3271011 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.7449. Min Act: -0.1700
Data Index: 3540389 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.7449. Min Act: -0.1700
Data Index: 4005337 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.7137. Min Act: -0.1700
Data Index: 1288088 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.6512. Min Act: -0.1700
Data Index: 3908054 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.5574. Min Act: -0.1700
Data Index: 6201211 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.5262. Min Act: -0.1700
Data Index: 4098702 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.5262. Min Act: -0.1700
Data Index: 1462945 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.4949. Min Act: -0.1700
Data Index: 1494762 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.4949. Min Act: -0.1700
Data Index: 2389235 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.4949. Min Act: -0.1700
Data Index: 2991278 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.4637. Min Act: -0.1700
Data Index: 8516691 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.4637. Min Act: -0.1700
Data Index: 6596671 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.4637. Min Act: -0.1700
Data Index: 5409230 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.4637. Min Act: -0.1700
Data Index: 288717 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.3699. Min Act: -0.1700
Data Index: 3605209 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9637. Min Range: -7.9637
Max Act: 7.3699. Min Act: -0.1700
Data Index: 288938 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19