Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3894 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.8168. Min Act: -0.1700
Data Index: 40450 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.7231. Min Act: -0.1700
Data Index: 554819 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.6606. Min Act: -0.1700
Data Index: 7432854 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.5981. Min Act: -0.1700
Data Index: 554837 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.5981. Min Act: -0.1700
Data Index: 6507516 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.5668. Min Act: -0.1700
Data Index: 4191892 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.5356. Min Act: -0.1700
Data Index: 4202545 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.4731. Min Act: -0.1700
Data Index: 420553 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.4731. Min Act: -0.1700
Data Index: 7179207 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.4106. Min Act: -0.1700
Data Index: 1352685 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.4106. Min Act: -0.1700
Data Index: 6679289 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.4106. Min Act: -0.1700
Data Index: 6496360 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.4106. Min Act: -0.1700
Data Index: 2749413 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.3481. Min Act: -0.1700
Data Index: 5147414 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.3793. Min Act: -0.1700
Data Index: 159458 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.4106. Min Act: -0.1700
Data Index: 3946261 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.3481. Min Act: -0.1700
Data Index: 4408769 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.3168. Min Act: -0.1700
Data Index: 925645 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.3793. Min Act: -0.1700
Data Index: 6635750 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8168. Min Range: -7.8168
Max Act: 7.2856. Min Act: -0.1700
Data Index: 3018280 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19