Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3797 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.7177. Min Act: -0.1700
Data Index: 6578785 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.4989. Min Act: -0.1700
Data Index: 4895894 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.4989. Min Act: -0.1700
Data Index: 3458632 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.4677. Min Act: -0.1700
Data Index: 5841565 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3739. Min Act: -0.1700
Data Index: 1163821 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.4364. Min Act: -0.1700
Data Index: 1287873 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.4364. Min Act: -0.1700
Data Index: 310845 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3114. Min Act: -0.1700
Data Index: 7985440 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3114. Min Act: -0.1700
Data Index: 8338858 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3427. Min Act: -0.1700
Data Index: 292758 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3427. Min Act: -0.1700
Data Index: 3526251 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3114. Min Act: -0.1700
Data Index: 7554629 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3114. Min Act: -0.1700
Data Index: 622648 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3427. Min Act: -0.1700
Data Index: 3070450 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3114. Min Act: -0.1700
Data Index: 6226643 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.2802. Min Act: -0.1700
Data Index: 1290134 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3114. Min Act: -0.1700
Data Index: 5899991 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.2802. Min Act: -0.1700
Data Index: 867423 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.3114. Min Act: -0.1700
Data Index: 3528342 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7177. Min Range: -5.7177
Max Act: 5.2489. Min Act: -0.1700
Data Index: 430752 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19