Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2618 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.5116. Min Act: -0.1700
Data Index: 2591882 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.5116. Min Act: -0.1700
Data Index: 2299230 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4960. Min Act: -0.1700
Data Index: 8127906 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4803. Min Act: -0.1700
Data Index: 3780650 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4646. Min Act: -0.1700
Data Index: 102227 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4646. Min Act: -0.1700
Data Index: 303019 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.5116. Min Act: -0.1700
Data Index: 6920629 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 5559412 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4490. Min Act: -0.1700
Data Index: 958406 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4646. Min Act: -0.1700
Data Index: 7806495 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4333. Min Act: -0.1700
Data Index: 5314208 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4333. Min Act: -0.1700
Data Index: 6505023 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4333. Min Act: -0.1700
Data Index: 4240697 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 6334613 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4803. Min Act: -0.1700
Data Index: 2206467 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 497830 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 3750118 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4176. Min Act: -0.1700
Data Index: 5203647 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4019. Min Act: -0.1700
Data Index: 1066676 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5116. Min Range: -3.5116
Max Act: 3.4019. Min Act: -0.1700
Data Index: 4675740 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19