Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2488 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.6306. Min Act: -0.1700
Data Index: 4263418 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.6619. Min Act: -0.1700
Data Index: 5419349 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.6619. Min Act: -0.1700
Data Index: 5923830 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5994. Min Act: -0.1700
Data Index: 7781838 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5681. Min Act: -0.1700
Data Index: 4033853 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5994. Min Act: -0.1700
Data Index: 6787321 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5681. Min Act: -0.1700
Data Index: 860458 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5681. Min Act: -0.1700
Data Index: 6998814 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5056. Min Act: -0.1700
Data Index: 7451837 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5369. Min Act: -0.1700
Data Index: 5113685 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5056. Min Act: -0.1700
Data Index: 7924895 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.5056. Min Act: -0.1700
Data Index: 3336908 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4744. Min Act: -0.1700
Data Index: 4082172 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4744. Min Act: -0.1700
Data Index: 5968129 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4744. Min Act: -0.1700
Data Index: 996752 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4744. Min Act: -0.1700
Data Index: 6683647 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4431. Min Act: -0.1700
Data Index: 7929313 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4119. Min Act: -0.1700
Data Index: 114229 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4119. Min Act: -0.1700
Data Index: 1598983 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6619. Min Range: -5.6619
Max Act: 5.4119. Min Act: -0.1700
Data Index: 1383424 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #19