Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5186 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.2835. Min Act: -0.1700
Data Index: 6126016 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.2835. Min Act: -0.1700
Data Index: 4128057 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.1585. Min Act: -0.1700
Data Index: 5037537 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.1273. Min Act: -0.1700
Data Index: 5203079 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.1273. Min Act: -0.1700
Data Index: 2933738 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0960. Min Act: -0.1700
Data Index: 2566154 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0960. Min Act: -0.1700
Data Index: 5383923 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0648. Min Act: -0.1700
Data Index: 4757392 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0648. Min Act: -0.1700
Data Index: 6969152 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0648. Min Act: -0.1700
Data Index: 7308226 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0648. Min Act: -0.1700
Data Index: 1794880 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0648. Min Act: -0.1700
Data Index: 2681064 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0335. Min Act: -0.1700
Data Index: 5075360 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0335. Min Act: -0.1700
Data Index: 2003297 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0335. Min Act: -0.1700
Data Index: 6126012 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0023. Min Act: -0.1700
Data Index: 7887364 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0335. Min Act: -0.1700
Data Index: 7612260 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0335. Min Act: -0.1700
Data Index: 1591435 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0023. Min Act: -0.1700
Data Index: 6126020 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2835. Min Range: -5.2835
Max Act: 5.0023. Min Act: -0.1700
Data Index: 4327730 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19