Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2641 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.4195. Min Act: -0.1700
Data Index: 4509159 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.3258. Min Act: -0.1700
Data Index: 7569758 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.3258. Min Act: -0.1700
Data Index: 7963256 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.3258. Min Act: -0.1700
Data Index: 6314920 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.2008. Min Act: -0.1700
Data Index: 360278 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1695. Min Act: -0.1700
Data Index: 3211374 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1695. Min Act: -0.1700
Data Index: 2313683 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1695. Min Act: -0.1700
Data Index: 2009444 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1695. Min Act: -0.1700
Data Index: 725594 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1695. Min Act: -0.1700
Data Index: 1038015 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1383. Min Act: -0.1700
Data Index: 6793482 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1070. Min Act: -0.1700
Data Index: 18540 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1695. Min Act: -0.1700
Data Index: 8321706 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1695. Min Act: -0.1700
Data Index: 4688853 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.0757. Min Act: -0.1700
Data Index: 7313034 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1070. Min Act: -0.1700
Data Index: 1944804 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.1070. Min Act: -0.1700
Data Index: 8655339 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.0757. Min Act: -0.1700
Data Index: 7524262 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.0757. Min Act: -0.1700
Data Index: 98895 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4195. Min Range: -4.4195
Max Act: 4.0757. Min Act: -0.1700
Data Index: 681059 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19