Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.7448. Min Act: -0.1700
Data Index: 7875609 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.7448. Min Act: -0.1700
Data Index: 5398875 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.5886. Min Act: -0.1700
Data Index: 3630604 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.5573. Min Act: -0.1700
Data Index: 6695681 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.5261. Min Act: -0.1700
Data Index: 6695680 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.4948. Min Act: -0.1700
Data Index: 2009044 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.4323. Min Act: -0.1700
Data Index: 5299266 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.3698. Min Act: -0.1700
Data Index: 4811943 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.3698. Min Act: -0.1700
Data Index: 7356453 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.3386. Min Act: -0.1700
Data Index: 2724420 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.3073. Min Act: -0.1700
Data Index: 4724337 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.2761. Min Act: -0.1700
Data Index: 221844 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.2448. Min Act: -0.1700
Data Index: 634216 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.2448. Min Act: -0.1700
Data Index: 8576639 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.2136. Min Act: -0.1700
Data Index: 5666531 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.2136. Min Act: -0.1700
Data Index: 670402 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.2136. Min Act: -0.1700
Data Index: 662349 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.2136. Min Act: -0.1700
Data Index: 8138246 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.1823. Min Act: -0.1700
Data Index: 4969310 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7448. Min Range: -5.7448
Max Act: 5.1823. Min Act: -0.1700
Data Index: 1100281 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19