Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4055 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.6074. Min Range: -8.6074
Max Act: 8.6074. Min Act: -0.1700
Data Index: 1272263 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6074. Min Range: -8.6074
Max Act: 8.2324. Min Act: -0.1700
Data Index: 1293424 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6074. Min Range: -8.6074
Max Act: 8.1699. Min Act: -0.1700
Data Index: 3425185 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6074. Min Range: -8.6074
Max Act: 8.1074. Min Act: -0.1700
Data Index: 3623363 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.9199. Min Act: -0.1700
Data Index: 6977626 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.9824. Min Act: -0.1700
Data Index: 3623977 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.9824. Min Act: -0.1700
Data Index: 654553 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.9199. Min Act: -0.1700
Data Index: 364353 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.9199. Min Act: -0.1700
Data Index: 2096080 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.9199. Min Act: -0.1700
Data Index: 3789582 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.8574. Min Act: -0.1700
Data Index: 1133409 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.9199. Min Act: -0.1700
Data Index: 3185785 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.8574. Min Act: -0.1700
Data Index: 4741799 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.7324. Min Act: -0.1700
Data Index: 1849658 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.7949. Min Act: -0.1700
Data Index: 8695629 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.7324. Min Act: -0.1700
Data Index: 838707 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.7949. Min Act: -0.1700
Data Index: 8097379 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.7949. Min Act: -0.1700
Data Index: 7865990 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.7949. Min Act: -0.1700
Data Index: 7225329 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6074. Min Range: -8.6074
Max Act: 7.7324. Min Act: -0.1700
Data Index: 5757965 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19