Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.2277. Min Act: -0.1700
Data Index: 8762230 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0558. Min Act: -0.1700
Data Index: 7064338 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2277. Min Range: -4.2277
Max Act: 4.0089. Min Act: -0.1700
Data Index: 7908909 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9621. Min Act: -0.1700
Data Index: 1414729 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9464. Min Act: -0.1700
Data Index: 5384 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9464. Min Act: -0.1700
Data Index: 3580710 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8995. Min Act: -0.1700
Data Index: 1680177 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.9152. Min Act: -0.1700
Data Index: 5656657 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8839. Min Act: -0.1700
Data Index: 8472411 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8683. Min Act: -0.1700
Data Index: 7654250 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8683. Min Act: -0.1700
Data Index: 3691967 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8526. Min Act: -0.1700
Data Index: 2529851 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8683. Min Act: -0.1700
Data Index: 8467133 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8526. Min Act: -0.1700
Data Index: 7235689 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8526. Min Act: -0.1700
Data Index: 2780223 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8526. Min Act: -0.1700
Data Index: 703310 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8370. Min Act: -0.1700
Data Index: 985337 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8370. Min Act: -0.1700
Data Index: 8405481 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8370. Min Act: -0.1700
Data Index: 7709816 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2277. Min Range: -4.2277
Max Act: 3.8214. Min Act: -0.1700
Data Index: 844490 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19