Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.4380. Min Act: -0.1700
Data Index: 7382914 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.4380. Min Act: -0.1700
Data Index: 1056158 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.4067. Min Act: -0.1700
Data Index: 1444054 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.3442. Min Act: -0.1700
Data Index: 4292473 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.2505. Min Act: -0.1700
Data Index: 7971700 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.2817. Min Act: -0.1700
Data Index: 8492748 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.3130. Min Act: -0.1700
Data Index: 3622123 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.2817. Min Act: -0.1700
Data Index: 382179 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.2505. Min Act: -0.1700
Data Index: 832466 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1880. Min Act: -0.1700
Data Index: 2238474 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1880. Min Act: -0.1700
Data Index: 3794952 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1880. Min Act: -0.1700
Data Index: 7640426 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1880. Min Act: -0.1700
Data Index: 4207647 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1880. Min Act: -0.1700
Data Index: 7055448 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1567. Min Act: -0.1700
Data Index: 1612271 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1567. Min Act: -0.1700
Data Index: 3248501 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1567. Min Act: -0.1700
Data Index: 996922 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1567. Min Act: -0.1700
Data Index: 742199 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.1255. Min Act: -0.1700
Data Index: 8106864 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4380. Min Range: -7.4380
Max Act: 7.0942. Min Act: -0.1700
Data Index: 1252258 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19