Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0175. Min Range: -4.0175
Max Act: 4.0175. Min Act: -0.1700
Data Index: 3342149 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.9862. Min Act: -0.1700
Data Index: 5177330 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.9862. Min Act: -0.1700
Data Index: 2222482 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.9549. Min Act: -0.1700
Data Index: 424413 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.8924. Min Act: -0.1700
Data Index: 3762875 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.8924. Min Act: -0.1700
Data Index: 5613250 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.8924. Min Act: -0.1700
Data Index: 4946080 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.8142. Min Act: -0.1700
Data Index: 5438114 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7986. Min Act: -0.1700
Data Index: 2281470 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7830. Min Act: -0.1700
Data Index: 8565322 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7673. Min Act: -0.1700
Data Index: 7160871 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7360. Min Act: -0.1700
Data Index: 1541542 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7517. Min Act: -0.1700
Data Index: 2203936 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7517. Min Act: -0.1700
Data Index: 5943743 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7360. Min Act: -0.1700
Data Index: 601214 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7204. Min Act: -0.1700
Data Index: 5753722 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.6891. Min Act: -0.1700
Data Index: 4272641 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7048. Min Act: -0.1700
Data Index: 5418641 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.7048. Min Act: -0.1700
Data Index: 4037016 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0175. Min Range: -4.0175
Max Act: 3.6891. Min Act: -0.1700
Data Index: 5078531 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19