Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1533 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1866. Min Range: -6.1866
Max Act: 6.1866. Min Act: -0.1700
Data Index: 347753 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.9991. Min Act: -0.1700
Data Index: 2977054 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.9679. Min Act: -0.1700
Data Index: 4665654 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.7804. Min Act: -0.1700
Data Index: 2587908 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.6866. Min Act: -0.1700
Data Index: 821464 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.6241. Min Act: -0.1700
Data Index: 2248015 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.6241. Min Act: -0.1700
Data Index: 3191185 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.5929. Min Act: -0.1700
Data Index: 5084736 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.5616. Min Act: -0.1700
Data Index: 2155513 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.5616. Min Act: -0.1700
Data Index: 691025 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.5929. Min Act: -0.1700
Data Index: 2059977 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.5304. Min Act: -0.1700
Data Index: 5632658 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.5616. Min Act: -0.1700
Data Index: 6876744 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.5304. Min Act: -0.1700
Data Index: 3364135 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.4991. Min Act: -0.1700
Data Index: 453097 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.4991. Min Act: -0.1700
Data Index: 2489834 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.4679. Min Act: -0.1700
Data Index: 8786303 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.4679. Min Act: -0.1700
Data Index: 4084680 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.4366. Min Act: -0.1700
Data Index: 4072184 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1866. Min Range: -6.1866
Max Act: 5.4366. Min Act: -0.1700
Data Index: 5054711 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19