Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1738 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.5044. Min Act: -0.1700
Data Index: 8587819 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.5044. Min Act: -0.1700
Data Index: 7427435 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.4106. Min Act: -0.1700
Data Index: 2119247 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.3169. Min Act: -0.1700
Data Index: 1127766 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.2544. Min Act: -0.1700
Data Index: 694790 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.2544. Min Act: -0.1700
Data Index: 5957417 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.2544. Min Act: -0.1700
Data Index: 2262407 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1294. Min Act: -0.1700
Data Index: 6602015 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1294. Min Act: -0.1700
Data Index: 1824614 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1294. Min Act: -0.1700
Data Index: 4968334 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1606. Min Act: -0.1700
Data Index: 2916175 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0981. Min Act: -0.1700
Data Index: 3004405 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0668. Min Act: -0.1700
Data Index: 6451939 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0356. Min Act: -0.1700
Data Index: 5465233 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0356. Min Act: -0.1700
Data Index: 6175061 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0356. Min Act: -0.1700
Data Index: 7122770 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0356. Min Act: -0.1700
Data Index: 8552965 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0356. Min Act: -0.1700
Data Index: 7122755 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0043. Min Act: -0.1700
Data Index: 6251783 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0356. Min Act: -0.1700
Data Index: 5820224 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19