Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4040 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.4204. Min Act: -0.1700
Data Index: 4998691 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.3266. Min Act: -0.1700
Data Index: 6744623 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.3266. Min Act: -0.1700
Data Index: 1916377 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.3579. Min Act: -0.1700
Data Index: 5239618 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2954. Min Act: -0.1700
Data Index: 4405787 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.3579. Min Act: -0.1700
Data Index: 922176 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2641. Min Act: -0.1700
Data Index: 1901577 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.3579. Min Act: -0.1700
Data Index: 1946175 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.3266. Min Act: -0.1700
Data Index: 8487152 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2641. Min Act: -0.1700
Data Index: 8770421 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2641. Min Act: -0.1700
Data Index: 4692245 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2641. Min Act: -0.1700
Data Index: 5832257 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2641. Min Act: -0.1700
Data Index: 1574841 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2641. Min Act: -0.1700
Data Index: 2786617 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2329. Min Act: -0.1700
Data Index: 3862205 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.1704. Min Act: -0.1700
Data Index: 8019164 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.2016. Min Act: -0.1700
Data Index: 503373 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.1391. Min Act: -0.1700
Data Index: 1166737 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.1704. Min Act: -0.1700
Data Index: 3431433 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4204. Min Range: -4.4204
Max Act: 4.1704. Min Act: -0.1700
Data Index: 996133 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19